This study analyzes future hydrological droughts in LCKW using the SWAT model and data from 2010-2021, evaluating the Streamflow Drought Index (SDI) for 5, 10, 25, and 50-year return periods (RP) for 2029 and 2039 under RCP4.5 and RCP8.5 scenarios. The model shows high accuracy (R² = 0.82, NSE = 0.78). Under RCP4.5, streamflow may increase by 34.74% and 18.74%, while RCP8.5 predicts significant decreases of 37.06% and 55.84%. Historical data reveal frequent short-term droughts during SDI-3, notably in 2014–2016 and 2020–2021, with SDI-6 indicating less frequent but severe droughts, especially in 2015 and 2020. Future projections under RCP8.5 suggest wors-ening drought conditions in 2029 and 2039, with critical drought periods from January to April and November. Wavelet analysis indicates a high risk of severe hydrological drought in LCKW due to low annual recurrence rates, with the highest drought severity over a 50-year RP. The study high-lights an increasing likelihood of frequent and severe droughts, particularly under high emission scenarios such as RCP8.5, which could result in significant water shortages and ecosystem disrup-tions. It emphasizes the significance of adaptive water resource management strategies in mitigating negative impacts on water security and ecosystem health.

The information of seismic damage of buildings in SAR images of different time phase, especially in SAR images after earthquake, is easily disturbed by other factors, which affects the accuracy of information discrimination. In order to identify and evaluate the distribution information of the seismic damage accurately and make full use of the abundant texture features in the SAR image. The conventional method of change detection based on texture features usually takes the pixel as the calculating unit. In this paper, a method of texture feature change detection of SAR images based on watershed segmentation algorithm is proposed. Based on the optimization of texture feature parameters, the feature parameters are segmented by the watershed segmentation algorithm, and the feature object image is obtained. This method introduces the idea of object oriented, and carries out the calculation of the difference map at the object level, Finally, the classification threshold value of different types of seismic damage types is selected, and the recognition of building damage is achieved. Taking the ALOS data before and after the earthquake in Yushu as an example to verify the effectiveness of the method, the overall accuracy of the building extraction is 88.9%, Compared with pixel-based methods, it is proved that the proposed method is effective.

In the process of sewage coagulation treatment, quartz sand is often used as a heavy medium to accelerate the settling rate of flocs, but it will adversely affect the removal efficiency of pollutants. The factors that affect the coagulation effect and can be controlled manually include the quartz sand dosage, coagulant dosage, sewage pH, stirring time, settling time, etc, their reasonable setting is critical to. This paper was to study the optimal conditions of quartz sand enhanced coagulation(QSEC), first, single-factor tests were conducted to preliminarily explore the optimal range of influencing factors, and then response surface methodology（RSM）tests were performed to accurately determine the optimums of significant factors. The results showed that the addition of quartz sand can’t improve the water quality of coagulation treatment, but it can significantly accelerate the coagulation settlement process, the quartz sand dosage, the coagulant dosage and sewage pH all impacted significantly on its coagulation effect, and existed inflection points. A model that could guide QSEC was obtained by RSM tests. The model optimization and experimental validation showed that the optimal QSEC conditions for treating domestic sewage were as follows: the polyaluminum chloride(PAC) dosage, cationic polyacrylamide(CPAM) dosage, the sewage pH, quartz sand dosage, stirring time and settling time were 0.97 g·L-1, 2.25 mg·L-1, 7.22, 2 g·L-1, 5 minutes and 30 minutes, respectively, and the turbidity of treated sewage was reduced to 1.15 NTU.

Degradation of environment quality is currently the prime cause of the recent occurrence of natural disasters; it also contributes in the increase of the area that is prone to natural disasters. This research is aimed to map the potential of areas around Pesanggrahan river in DKI Jakarta by segmenting the Digital Elevation Model derived from LIDAR data. The objective of this segmentation is to find the watershed lines of the DEM image. Data processing in this research is using LIDAR data which take the ground surface data, which is overlaid with Jakarta river map and subsequently, the data is then segmented the image. The expected result of the research is the flood potential area information, especially along the Pesanggrahan river in South Jakarta.

This research explores the application of Support Vector Machine (SVM) and Digital Surface Models (DSM) derived from Unmanned Aerial Vehicle (UAV) data for a vertical-horizontal classification of mangrove ecosystems in Tongke-tongke and Samataring Village. The study focuses on integrating high-resolution DSM subtracted from Digital Terrain Models (DTM) to classify mangrove vegetation into sixteen distinct vertical-horizontal classes based on vegetation type and elevation. The analysis revealed that older mangroves, particularly those within the 25-35 meters elevation range, dominate the landscape, accounting for 43.40% of the total classified area. This dominance suggests a mature and ecologically stable mangrove ecosystem, which is crucial for biodiversity conservation and carbon storage. The study demonstrates the effectiveness of SVM and UAV technologies in providing detailed and accurate ecological assessments of mangrove forests. The classification results contribute valuable insights into the structural diversity and health of mangrove ecosystems, facilitating targeted conservation and management strategies. Additionally, the research highlights the utility of advanced remote sensing and machine learning techniques in enhancing the precision of environmental monitoring and the assessment of carbon sequestration capabilities within mangrove ecosystems. The findings underscore the potential of UAV-based remote sensing for ecological studies, offering a replicable method for similar assessments in other regions, thereby supporting global environmental management and climate action initiatives.

In Ethiopia, farmers have changed cropland to Eucalyptus globulus plantations for construction, fuelwood and economic benefits. However, it has adverse effects on soil properties. The investigation was, therefore, to evaluate the impact of Eucalyptus globulus plantations on soil properties in northwestern Ethiopia. About 30 soil samples were collected from two soil depths (0-20 and 20-40 cm) and three land uses (Eucalyptus globulus plantations, cropland and grazing land) with five replications. Soil properties were analyzed using a two-way analysis of variance (ANOVA). Based on the result, soil properties such as silt particles, moisture content (MC), organic matter (OM), total nitrogen (TN) and cation exchange capacity (CEC) were significantly higher under the soil of Eucalyptus globulus plantations than in cropland and grazing land. Whereas the lower contents of bulk density (BD), soil pH, available phosphorus (AP), electrical conductivity (EC) and exchangeable bases (Ca, Mg, K, and Na) were recorded in Eucalyptus globulus plantations. Besides, clay, BD, MC, pH, EC, CEC, percent base saturation (PBS) and basic cations increased with soil depth while decreasing sand, silt, TP, OM and AP. The basic cations ( Ca, Mg, K), PBS and AP decreased in the soil of the 25-year old Eucalyptus globulus plantation compared to cropland by 38%, 36%, 43 %, 45% and 47% and grazing land by 56%, 60%, 76 %, 60% and 56%, respectively. Therefore, appropriate and effective land use management principles should be implemented in the study area.

Attention mechanisms have become a fundamental component of deep learning, including the field of computer vision. The key idea behind attention in computer vision is to help the model focus on the relevant spatial regions of the input image, rather than treating all regions equally. The traditional approaches to attention mechanisms in computer vision often suffer from distribution inconsistencies in the attention maps, resulting in sharp transitions that negatively affect model’s focus and lead to poor generalization on complex shapes. The problem of spatial incoherence is particularly pronounced in the task of semantic segmentation, where accurate pixel-level predictions require a detailed understanding of the spatial relationships within the image. In this paper, we propose an attention mechanism called Smooth Attention designed for convolutional neural networks to address the problem of spatial inconsistency in attention maps through multidimensional spatial smoothing. We conduct a series of experiments to evaluate the effectiveness of the proposed mechanism and demonstrate its superior performance compared to traditional methods.

Lake sediment records are of great importance for understanding the evolution of watershed environments. Various studies have been carried out to constrain the depositional ages of lake sediments and examine their physical, chemical, and biological characteristics, aiming to construct historical vegetation, environment and climate patterns in Chinese lake watersheds. In this study, we obtained relevant literature on lake sediment records by searching the key word 'age-depth' from the databases – Web of Science and China National Knowledge Infrastructure (CNKI, the largest Chinese academic database). We analyzed the literature based on its type (published in a Chinese/English journal or as a Master’s/PhD thesis), period of publication, journal (if published in a journal), key authors, study area, dating scale, and main aims. The results suggest that the lakes in the plateau regions are the most popular research topic typically covering 100–200 years (short-term) and 500–30,000 years (long-term). The literature focuses on a wide range of topics, from past environmental evolution in the watershed to lake ecology, and provides a solid foundation for better understanding regional climate change and the preservation of lake environments and ecosystems. In the future, resulting data from environmental reconstruction with lake sediments will be needed to integrate with emerging information processing technologies (e.g., artificial intelligence and meta-analysis), to disentangle the complex interplay between Earth surface processes and global climate change; furthermore, strengthening interdisciplinary collaboration will deepen our comprehension of man-land relationship and promote the sustainable management of lake ecosystems in the context of global climate change.

Aiming at the problems of inaccurate segmentation of long object and information loss of small object in real-time semantic segmentation algorithm, this paper proposes a lightweight multi-branch real-time semantic segmentation network based on BiseNetV2. The new auxiliary branch makes full use of spatial details and context information to cover the long object in the field of view. Meanwhile, in order to ensure the inference speed of the model, the asymmetric convolution is used in each stage of the auxiliary branch to design a structure with low computational complexity. In the multi-branch fusion stage, the alignment and fusion module is designed to provide guidance information for deep and shallow feature mapping, so as to make up for the problem of feature misalignment in the fusion of information at different scales, and thus reduce the loss of small target information. In order to further improve the model’s awareness of key information, a global context module is designed to capture the most important features in the input data. The proposed network uses NVIDIA GeForce RTX 3080 Laptop GPU experiment, on the road street view data set Cityscapes and CamVid average occurring simultaneously ratio reached 77.1% and 78.4% respectively, with running speed of 127 frames/s respectively and 112 frames/s. The experimental results show that the proposed algorithm can achieve real-time segmentation and improve the accuracy significantly, showing good semantic segmentation performance

Open-vocabulary learning has recently gained prominence as a means to enable image segmentation for arbitrary categories based on textual descriptions. This advancement has extended the applicability of segmentation systems to a broader range of generally purpose scenarios. However, current methods often revolve around specialized architectures and parameters tailored to specific segmentation tasks, resulting in a fragmented landscape of segmentation models. In response to these challenges, we introduce OVAMTSeg, a versatile framework designed for Open-Vocabulary and Multitask Image Segmentation. OVAMTSeg harnesses adaptive prompt learning to empower the model to capture category-sensitive concepts, enhancing its robustness across diverse multi-task and scenario contexts. Text prompts are employed to effectively capture semantic and contextual features of the text, while cross-attention and cross-modal interactions enable the fusion of image and text features. Furthermore, a transformer-based decoder is incorporated for dense prediction. Extensive experimental results underscore the effectiveness of OVAMTSeg, showcasing its state-of-the-art performance and superior generalization capabilities across three segmentation tasks. Notable achievements include a 47.5 mIoU in referring expression segmentation, 51.6 mIoU on Pascal-VOC with four unseen classes, 46.6 mIoU on Pascal-Context in zero-shot segmentation, 65.9 mIoU on Pascal-5i, and 35.7 mIoU on COCO-20i datasets for one-shot segmentation.

Pulmonary Embolism (PE) is the obstruction of blood arteries in the lungs by a blood clot. The mortality risk for PE is approximately 30%. Detecting pulmonary embolism in the segmental arteries of the lung is more challenging than in the main arteries and is very prone to being missed. A computer-based approach was created in this work to automatically identify pulmonary embolism in the segmental arteries using computed tomography images. The system's infrastructure includes an enhanced Mask R-CNN deep neural network that has been trained with images containing PE. The network accurately identifies the location of the pulmonary embolism on the computed tomography picture and successfully extracts its borders. The investigation was conducted by generating a local dataset. The study's performance was evaluated using pulmonary embolisms identified manually by the expert radiologist. The sensitivity, specificity, accuracy, dice coefficient, and Jaccard index values for 2130 pictures were 96.4%, 93.5%, 96.1%, 0.96, and 0.90, respectively. The improved Mask R-CNN model has demonstrated superior performance when compared to the traditional Mask R-CNN and U-Net models. This high-performance technology is designed to identify pulmonary embolism and will aid professionals in assessing the size of the embolism.

We propose a novel unsupervised semantic segmentation method for fast and accurate flood area detection utilizing color images acquired from Unmanned Aerial Vehicles (UAVs). To the best of our knowledge, this is the first fully unsupervised method for flood area segmentation in color images captured by UAVs, without the need of pre-disaster images. The proposed framework addresses the problem of flood segmentation based on parameter-free calculated masks and unsupervised image analysis techniques. First, a fully unsupervised algorithm gradually excludes areas classified as non-flood utilizing calculated masks over each component of the LAB colorspace, as well an RGB vegetation index and the detected edges of the original image. Unsupervised image analysis techniques, such as distance transform, are then applied, producing a probability map for the location of flooded areas. Finally, flood detection is obtained by applying the hysteresis thresholding segmentation. The proposed method is tested and compared with variations, and other supervised methods in two public datasets, consisting of 953 color images in total, yielding high-performance results, with 87.4% and 80.9% overall accuracy and F1-Score, respectively. The results and computational efficiency of the proposed method show that it is suitable for on board data execution and decision-making during UAVs flight.

Interaction between multiple phases especially liquid-gas is one of the most common phenomena in industrial systems. Computer Vision enables modern systems to derive an automated and robust image-processing technique to address this issue. However, diverse experimental conditions still make it a challenging task to overcome. In Deep Learning, instance segmentation has created a niche in various computer vision applications as it aims to provide different instance IDs to objects belonging to the same class. In this paper, we propose a novel approach employing the YOLO (You Look Only Once) an end-to-end deep learning architecture for the detection and segmentation of bubbles in fluid flows. YOLOv5 offers significant improvements in both speed and accuracy compared to its predecessors like YOLOv3. Therefore, we train the YOLOv5 network on a dataset consisting of annotated images representing instances of bubbles across varied fluid flow environments. This paper provides both qualitative and quantitative evaluation of three YOLOv5 networks (small, medium, and extra-large) in detecting and segmenting bubbles with high accuracy and efficiency. Based on the metrics all three YOLOv5 models achieved high precision above 0.98 for bounding box detection and 0.97 for segmentation mask, and high recall value greater than 0.97 for box and 0.96 for mask quality was achieved. The achieved results indicate that the models accurately localize bubbles within the image frame, and distinguish bubble pixels from the background. Also, mean average precision (mAP50-95) consistently exceeds 0.84 across all models for the bounding box and 0.73 for the segmentation mask. The ascertained results emphasize the potential of YOLOv5 architecture as a powerful tool for automated bubble analysis in real-world applications. Our research contributes to advancing the field of deep neural networks in fluid systems and provides a fresh approach for future developments in automated bubble analysis.

The segmentation of abnormal regions is vital in smart manufacturing. However, the existing segmentation system for detecting sauce-packet leakage on intelligent sensors encounters an issue of imaging blurring caused by uneven illumination. This issue adversely affects segmentation performance, thereby impeding the rapid production of industrial assembly lines. To alleviate this issue, we propose the two-stage Illumination-aware Sauce-packet Leakage Segmentation (ISLS) method for intelligent sensors. The ISLS comprises two main stages: Illumination-aware region enhancement and leakage region segmentation. In the first stage, YOLO-Fastestv2 is employed to capture the Region of Interest (ROI), which reduces redundancy computations. Additionally, we propose an image enhancement to relieve the impact of uneven illumination, enhancing the texture details of ROI. In the second stage, we propose a novel feature extraction network. Specifically, we propose the Multi-scale Feature Fusion Module (MFFM) and the Sequential Self-Attention Mechanism (SSAM) to capture discriminative representations of leakage. The multi-level features are fused by MFFM with a small number of parameters, which capture leakage semantics at different scales. The SSAM realizes the enhancement of valid features and the suppression of invalid features by adaptive weighting of spatial and channel dimensions. Furthermore, we generated a self-built dataset of sauce-packets, including 606 images with various leakage areas. Comprehensive experiments demonstrate that our ISLS method shows better results than several state-of-the-art methods, with additional performance analyses deployed on intelligent sensors to affirm the effectiveness of our proposed method. Our code is available at https://github.com/LSJ5106/SauceDetect.

Image segmentation and classification still represent an active area of research since no universal solution can be identified. Established segmentation algorithms like thresholding are problem specific, treat well the easy cases and mostly relied on single parameter i.e intensity. Machine learning approaches offer alternatives where predefined features are combined into different classifiers. On the other hand, the outcome of machine learning is only as good as the underlying feature space. Differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical objects, called invariants. In this way, the geometrical features form a high-dimensional feature space for each pixel, where original objects can be resolved. Alternatives based on the geometry of the image scale-invariant interest points have been exploited successfully in the field of computer vision. Here, we integrate geometrical feature extraction based on signal processing, machine learning, and input relying on domain knowledge. The approach is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application, we demonstrate powerful image classification functionality based on the same principles, which was applied to the HeLa and HEp-2 data sets. Obtained results demonstrate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches.

The task of weakly supervised point cloud semantic segmentation has received widespread attention and also has been widely used in autonomous driving, robotics, and modern industries. Due to the high dimensionality and large volume of point cloud data, many technical difficulties appeal to weakly supervised semantic processing, especially segmentation. However, weakly-supervised schemes usually provide only partial labelling information of the underlying point cloud data and thus need to effectively extract local features, geometric information, and contextual relationships only using these limited labelled data for supervised learning. To improve weakly-supervised semantic segmentation, we propose a novel segmentation network through the boundary-based feature aggregation based on a K-NN algorithm with down-sampling operation, and also introduce the smoothness loss and Siamese loss for effective segmentation. The experiments on public datasets demonstrate that our presented segmentation method exceeds most of the existing fully supervised and weakly-supervised methods in terms of mIoU. Specifically, our network has high segmentation accuracy on the labels of objects with similar geometrical structures, such as ceiling, wall, floor, chair and table, reaching 91.2%, 98.8%, 83.3%, 75.3% and 80.2%, respectively. Extensive experiments also illustrate its robustness, effectiveness, and generalization of the proposed weakly supervised segmentation network.

Medical image segmentation is a critical step in various healthcare applications, aiding in diagnosis, treatment planning, and disease monitoring. In this study, we investigate the efficacy of a segmentation approach based on the 2D wavelet transform. Leveraging a dataset comprising 10 diverse medical images, we evaluate the performance of our segmentation method using three key metrics: accuracy, precision, and recall. Our findings demonstrate that the proposed approach enhances segmentation accuracy, offering promising results compared to existing methods. By harnessing the multi-resolution feature extraction capabilities of the 2D wavelet transform, our method achieves improved delineation of medical image structures, paving the way for more accurate and efficient healthcare interventions.

Depth-sensing technology has led to broad applications of inexpensive depth cameras that can capture human motion and scenes in 3D space. Background subtraction algorithms can be improved by fusing color and depth cues, thereby allowing many issues encountered in classical color segmentation to be solved. In this paper, we propose a new fusion method that combines depth and color information for foreground segmentation based on an advanced color-based algorithm. First, a background model and a depth model are developed. Then, based on these models, we propose a new updating strategy that can eliminate ghosting and black shadows almost completely. Extensive experiments have been performed to compare the proposed algorithm with other, conventional RGB-D algorithms. The experimental results suggest that our method extracts foregrounds with higher effectiveness and efficiency.

Glaucoma, a global leading cause of blindness, necessitates accurate segmentation of the optic disc (OD) and optic cup (OC) for effective screening. However, existing segmentation methods based on convolutional neural networks (CNNs) suffer from high computational complexity and long inference times. In this paper, we propose an end-to-end segmentation method for the OD and OC using a lightweight MobileNetv3 as the feature extraction network. Our approach incorporates boundary branches and an adversarial learning network to achieve multi-label segmentation of the OD and OC. We evaluate the proposed method on three publicly available datasets: Drishti-GS, RIM-ONE-r3, and REFUGE. The experimental results demonstrate segmentation accuracies of 0.974/0.900, 0.966/0.875, and 0.962/0.880 for the OD and OC on the respective datasets, while significantly reducing inference time.

Tsallis entropy has been widely used in image thresholding because of its non-extensive properties. The non-extensive parameter q contained in this entropy plays an important role in various adaptive algorithms and has been successfully applied in bi-level image thresholding. In this paper, the relationships between parameter q and pixels’ long-range correlations have been further studied within multi-threshold image segmentation. It is found that the pixels’ correlations are remarkable and stable for images generated by a known physical principle, such as infrared images and medical CT images. And the corresponding non-extensive parameter q can be evaluated by using self-adaptive Tsallis entropy algorithm. The results of this algorithm are compared with those of Shannon entropy algorithm and the original Tsallis entropy algorithm, in terms of quantitative image quality evaluation metrics PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity). Furthermore, we observed that for image series with the same background, the q values determined by the adaptive algorithm are consistently kept in a narrow range. Therefore, similar or identical scenes during imaging would produce similar strength of long-range correlations, which provides potential applications for unsupervised image processing.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions.

The nine plateau lake watersheds in Yunnan are important ecological security barriers for southwest China, and the prevention and control of landslides are important considerations in the management of these watersheds. Taking Dianchi Lake watershed as a typical study area, this paper puts forward an improved comprehensive process of landslide susceptibility evalua-tion, and discusses the model’s sensitivity regarding susceptibility to landslides. The compre-hensive process is based on the weight of evidence method (WoE) and integrates many analyti-cal techniques, such as cross-validation, multi-quantile cumulative Student’s comprehensive weight analysis, independence tests, step-by-step modeling, ROC analysis and ROC-based sus-ceptibility zoning. This paper established fourteen models, with high accuracy and validity AUC, reaching 0.83-0.87 and 0.85-0.88, respectively. Moreover, according to the susceptibility zoning map compiled using the optimal model, 80% of landslides can be predicted in the very high and high susceptibility zones, which only account for 19.58% of the study area. Finally, the strategies for geological disaster prevention and ecological restoration deployment were put forward, providing great guiding significance for deeply understanding the landslide susceptibility of lake watersheds (Dianchi Lake) in Yunnan Plateau and guiding the planning and deployment of landslide prevention and mitigation activities and ecological restoration in the watershed.

Mobile health technologies enable continuous, quantitative assessment of mobility and gait in real-world environments, facilitating early diagnosis of gait disorders, disease progression monitoring, and prediction of adverse events like falls. Traditionally, mobile gait assessment predominantly relied on body-fixed sensors positioned at the feet or lower trunk. Here, we investigate the potential of an algorithm utilizing an ear-worn motion sensor for spatiotemporal segmentation of gait patterns. We collected 3D acceleration profiles from the ear-worn sensor during varied walking speeds in 53 healthy adults. Temporal convolutional networks were trained to detect stepping sequences and predict spatial relations between steps. The resulting algorithm, mEar, accurately detects initial and final ground contacts (F1 score of 99% and 91%, respectively). It enables determination of temporal and spatial gait cycle characteristics (among others stride time and stride length) with good to excellent validity at a precision sufficient to monitor clinically relevant changes in walking speed, stride-to-stride variability, and side asymmetry. This study highlights the ear as a viable site for monitoring gait and proposes its potential integration with in-ear vital sign monitoring. Such integration offers a practical approach to comprehensive health monitoring and telemedical applications, by integrating multiple sensors in a single anatomical location.

Air pollution has recently gained much attention from the general population. Despite pollution control being an issue in both urban and rural regions, most of the available research has concentrated on urban districts. Hence, investigations into how urban-rural transition affects PM2.5 are warranted within the framework of urban-rural integration. Using the Yellow River Basin as a case study, this study employed the entropy method and Analytic Hierarchy Process (AHP) to uncover the extent of urban-rural transformation. It then used the spatial autocorrelation method to investigate the spatiotemporal features of PM2.5 and the spatial econometric model to investigate the mechanisms that influence the relationship between urban-rural transformation and PM2.5. The results are as follows: (1) Over time, there was a discernible upward tendency in the change in urban-rural areas. The development has progressed from asymmetrical north-east and south-west elevations to a more balanced pattern of north-east, middle-east, and west-west elevations. (2) The PM2.5 concentration increased steadily, then fluctuated, and finally decreased. Notably, the general pattern has not changed much, and it is high in the east and low in the west. (3) Different subsystems of the urban-rural transformation have different impacts on air pollution at different stages. The influence of industrial transformation (IT) on PM2.5 showed an inverted “N-shaped” curve of negative-positive-negative changes, and the industrial structure played a leading role in the spatiotemporal evolution of PM2.5. Currently, an inverted "U-shaped" curve forms the left side of the impact of population transition (PT) on PM2.5. Land development (LT) has a "U-shaped" curve for its effect on PM2.5. This research provides a new perspective on the topic of PM2.5 and its connection to urban-rural integration, which is crucial to understanding the dynamics of this shift. To achieve its goal of high-quality development, it supports regional initiatives to reduce PM2.5 emissions in the Yellow River Basin. Moreover, it can provide a reference for decision-makers in the world’s densely populated areas that suffer from serious air pollution.

Nanling Mountain region is a typical southern hilly region, which plays an important ecological and environmental protection role in China's overall land protection pattern. Based on the remote sensing image data of Longnan City in Nanling Mountain in 2013, 2018 and 2023, this paper interpreted the land use type and analyzed the land use transfer situation by using Land use transfer flow, and Land use transfer matrix. At the same time, based on the remote sensing Ecological index (RSEI) model, the ecological environment quality of Longnan City from 2013 to 2023 was retrieved. The temporal and spatial response model of ecological environment quality to land use transfer in Longnan City from 2013 to 2023 was discussed based on Spatial autocorrelation and Geographic detector. The results show that from 2013 to 2023, the decrease of forest land (16.23km²) and the increase of construction land (13.25km²) were the main land use transfer in Longnan City. The ecological environment index of Longnan City in 2013, 2018 and 2023 was 0.789, 0.917 and 0.872, respectively, showing a trend of "first rising and then decreasing". The ecological environment quality in the north of Longnan City was significantly lower than that in the south, and the poor ecological quality area appeared in and around the northern main urban area, showing a trend of "inward contraction". Forest land, garden land, grassland, cultivated land and water area have a positive impact on ecological environment quality, while traffic land, construction land and other land have a negative impact on ecological environment quality. The response of ecological environment quality to different land use transfer modes is related to the change of the overall ecological environment quality. The interaction between LUCC and other factors had a great impact on the evolution of ecological environment quality in Longnan City.

Large datasets play a crucial role in the progression of surgical robotics, facilitating advancements in the fields of surgical task recognition and automation. Moreover, public datasets enable the comparative analysis of various algorithms and methodologies, thereby assessing their effectiveness and performance. The ROSMA (Robotics Surgical Maneuvers) dataset provides 206 trials of common surgical training tasks performed with the da Vinci Research Kit (dVRK). In this work, we extend ROSMA dataset with two annotated subsets: ROSMAT24, which contains bounding box annotations for instrument detection, and ROSMAG40, which contains high and low level gesture annotations. We propose an annotation method that provides independent labels for the right-handed tool and the left-handed tool. For instrument identification, we validate our proposal with a YOLOv4 model in two experimental scenarios. We demonstrate the generalization capabilities of the network to detect instruments in unseen scenarios. For gesture segmentation, we propose two label categories: high-level annotations that describe gestures at a maneuvers level, and low-level annotations that describe gestures at a fine-grain level. To validate this proposal, we have designed a recurrent neural network based on a bidirectional long-short term memory layer. We present results for four cross-validation experimental setups, reaching up to a 77.35% mAP.

With the rapid developments that have been made in computer vision and computer technology, semantic segmentation of high-resolution images has emerged as a mainstream and challenging task. The, segmentation of water areas remains a complex task due to the similar features between water areas or between water areas and other land objects. Meanwhile, since coastlines and riverbanks are typically presented in irregular shapes, it is difficult to obtain the categories of pixels at boundaries. This paper proposed the use of a Water-Land Boundary Attention Network (WLBANet) to improve the accuracy of pixels at boundaries between water and land. This network also reinforced the performance of contextual information extraction into distinguishing between water areas and other land objects. To prove the validity of this proposed network, WLBANet was performed on the Water Land Dataset (WLD), which is also by this paper, and which contains water areas and other land objects categories. The results demonstrates that the proposed method has significant effectiveness.

In the era of massive construction, damaged and aging infrastructure are becoming more common. Defects, such as cracking, spalling, etc., are main types of structural damage that widely occur. Hence, ensuring the safe operation existing infrastructure through health monitoring has emerged as an important challenge facing structural engineers. In recent years, intelligent approaches, such as data driven machine and deep learning crack detection, gradually dominate over traditional methods. Among them, the semantic segmentation using deep learning models is a process of characterization of accurate location and portrait of cracks using pixel level classification. Most available studies rely on single model knowledge to perform this task. However, it is well-known that the single model might suffer from low variance and low ability to generalize in case of data alteration. By leveraging the ensemble deep learning philosophy, a novel corporative semantic segmentation of concrete cracks method called Co-CrackSegment is proposed. Firstly, five models, namely the U-net, SegNet, DeepCrack19, DeepLabV3-ResNet50, and DeepLabV3-ResNet101 are trained to serve as core models for the ensemble model Co-CrackSegment. To build the ensemble model Co-CrackSegment, a new iterative approach based on the best evaluation metrics, namely the dice score, IoU, pixel accuracy, precision, and recall metrics is developed. Results show that the Co-CrackSegment exhibits a prominent performance compared to core models and weighted average ensemble by means of the considered best statistical metrics.

Biogeography research is flawed by the poor understanding of microbial distributions due to the lack of a systematic research framework, especially regarding appropriate study units. By combining pure culture and molecular methods, we studied the biogeographic patterns of nematode-trapping fungi by collecting and analysing 2,250 specimens from 228 sites in Yunnan Province, China. We found typical watershed patterns at the species and genetic levels of nematode-trapping fungi. The results showed that microbial biogeography could be better understood by 1) using watersheds as research units, 2) removing the coverup of widespread species, and 3) applying good sampling efforts and strategies. We suggest that watersheds could help unify the understanding of the biogeographic patterns of animals, plants, and microbes and may also help account for the historical and contemporary factors driving species distributions.

We evaluated the potential of using fish species and functional traits as indicators of land use impacts to fish assemblages. We used environmental data collected at multiple spatial scales (local, reach, and upstream catchment) for 19 tributary and main stem sites in the Nolichucky River watershed in Tennessee. Canonical correspondence analyses showed that temperature, elevation, specific conductivity, sediment yield, impervious surfaces, and row crop cover at the catchment scale were strongly associated with fish assemblage structure, as well as forest cover from all three spatial scales. Blocked indicator species analysis, with stream size as the block, showed that significantly strong indicators of the least-impacted riparian land use condition (≥60% forest cover) were Saffron Shiner (Notropis rubricroceus), Rainbow Trout (Oncorhyncus mykiss), Longnose Dace (Rhynichthys cataractae), Creek Chub (Semotilus atromaculatus), and Mottled Sculpin (Cottus bairdi). Traits indicative of the least-impacted sites were the herbivorous trophic guild, mean female age-at-maturity, longevity, rock-gravel spawners, montane geology and pelagic swimmers. Specific conductivity was strongly related to multiple catchment-scale land use variables, and was a strong local-scale influence on fish assemblage structure. Our results show promise for using a relatively common but endemic southern Appalachian fish species, the Saffron Shiner, as an indicator for land-use related impacts to these streams.

Plant phenotype plays an important role in crop breeding and planting. Leaf phenotype is an important part of plant phenotype. In order to analyze the leaf phenotype, the target leaf is required to be segmented from the complex background image. In this paper, an automatic soybean leaf segmentation method based on object detection and interactive segmentation models is proposed. Firstly, the Libra R-CNN object detection algorithm is used to detect all soybean leaves in the image. Then, based on the idea that the target soybean leaf is located in the center of the image and the area is large, the detection bounding box of the target leaf is selected. In order not to destroy the segmentation result, the bounding box is optimized to completely enclose the whole leaf. Finally, according to the optimized bounding box, the prior channels of foreground and background are constructed using Gaussian model. The two channels together with the original image are as the input of the interactive object segmentation with inside-outside guidance model to segment the target soybean leaf. A large number of qualitative and quantitative experimental results show that the method has high segmentation accuracy and strong generalization capacity.

Groundwater is becoming increasingly important in the Pacific Northwest of the USA due to declining snowpack volumes and shifts in precipitation type and timing, all connected with climate change. The Upper Williamson Basin of the Klamath Watershed is a groundwater dominated watershed with massive fluctuations in year-to-year streamflow volumes over the past four decades, including the complete absence of any live flow for several years. The precise relationship between groundwater and streamflow in the basin has been difficult to assess due to a limited number of monitoring wells and significant gaps in the water level time history. To address this challenge, we use a novel imputation technique that leverages Earth observations and machine learning to impute gaps in water level records. We use these more complete datasets to compute a groundwater storage change time series for the basin. We show that groundwater storage is highly correlated to streamflow and that groundwater storage is correlated to rainfall with a three- to four-year delay that appears variable depending on groundwater storage volumes. The tools and relationships we present make it possible for water managers to estimate when streamflows will return to the basin and be more informed to support better management.

This article presents a succinct overview of the progress, obstacles, and uses of semantic segmentation and instance segmentation within the forestry domain. The objective of this review is to conduct a critical analysis of the current literature pertaining to segmentation techniques and provide a methodical summary of their impact on forestry-related activities, including but not limited to tree species classification, forest inventory, and ecological monitoring such as retrieval of dominant tree species. Through the process of synthesizing pivotal discoveries from multiple studies, this comprehensive analysis provides valuable perspectives on the present status of research and highlights prospective areas for further exploration. The primary topics addressed encompass the approach employed for executing the examination, the fundamental discoveries associated with semantic segmentation and instance segmentation in the domain of forestry, and the ramifications of these discoveries for the discipline. The results indicate that the utilization of semantic segmentation methods has been efficacious in the field of forestry for the precise identification of tree species. Such methods also aid in tracking of deforested regions over the course of time by separating other land-use classes from forested regions. Additionally, the employment of instance segmentation techniques exhibits potential in the demarcation of individual trees. Instance segmentation offers promising results due to deep learning models based on forest point clouds. However, several challenges persist in the successful implementation of semantic segmentation methods such as the presence of occlusions, overlapping branches, and intricate structures hampers the accurate segmentation of trees. Additionally, instance segmentation approaches that utilize models are mostly trained by using laser scanning data based on forest types which are typically trained on specific laser scanning data and forest types that create limitations in generalization from high to low resolution point clouds. Due to this reason, the existing approaches often struggle with handling these complex structures, leading to the need for manual methods for extracting measurements from forest point clouds. The review culminates by underscoring the necessity for additional research to tackle current obstacles and augment the precision and relevance of segmentation methodologies in the field of forestry. In general, the present article provides a significant reference for scholars and professionals who are interested in utilizing segmentation techniques in the field of forestry.

This research introduces a pioneering solution to the challenges posed by gastrointestinal tract (GI) cancer in radiation therapy, focusing on the imperative task of precise organ segmentation for minimizing radiation-induced damage. GI imaging has historically used manual demarcation, which is laborious and uncomfortable for patients. We address this by introducing the ResECA-U-Net deep learning model, a novel combination of the UNet and ResNet34 architectures. Furthermore, we further augment its functionality by incorporating the Efficient Channel Attention (ECA-Net) methodology. By utilizing data from the UW-Madison Carbone Cancer Centre, we carefully investigate several image processing techniques designed to capture critical local characteristics. With its foundation in computer vision concepts, the ResECA-U-Net model is excellent at extracting fine details from GI images. Sophisticated metrics such as intersection over union (IoU) and the dice coefficient are used to evaluate performance. Our study's outcomes demonstrate the effectiveness of the suggested method, yielding an impressive 96.27% Dice coefficient and 91.48% IoU. These results highlight the significant contribution that our strategy has made to the advancement of cancer therapy. Beyond its scientific merits, this work has the potential to significantly enhance cancer patients' quality of life and provide better long-term outcomes. Our work is a significant step towards automating and optimizing the segmentation process, which can potentially change how GI cancer is treated completely.

Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, suitable for complex vegetable field environments and resource-limited laser weeding devices.

Nature-based solutions (NbS) rapidly develop globally to address societal challenges and provide human well-being and biodiversity. Watershed restoration plays an essential role in enhancing the ecological and socio-economic benefits of the region. The design and implementation of watershed restoration projects play a crucial role in their effectiveness, and NbS has been applied as a concept in ecosystem-related projects. This paper provides an idea to evaluate the design or implementation of watershed restoration projects based on the eight criteria proposed by the IUCN Global Standard for Nature-Based Solutions and to adjust the projects based on the evaluation results. The aim is to standardize the implementation process of watershed restoration projects to achieve more significant benefits and practically apply the concept of NbS in watershed restoration. implementation scheme of the Shan-Shui Initiative in the Jiulong River Watershed and concludes that the method is feasible in evaluating and improving the design and implementation scheme of ecological restoration projects in the actual basin. According to the assessment results, the degree of matching based on NbS for the implementation scheme of the Jiulong River Watershed Shan-Shui Initiative is 73%, which meets the criteria of NbS but needs to be improved in terms of monitoring and assessment, synergistic management, and benefit trade-offs.

Remote Sensing and Geographic Information System are recognized as crucial instruments for conducting geographical and geospatial research. RS and GIS technology was employed to assess the morphological Characteristics of the Kasura River Watershed situated within the Parbhani and Jalna Districts of Maharashtra, India. The entire drainage area of the Kasura River basin measures 490.13 square kilometers (km²). Various morphometric characteristic were calculated and examined, encompassing linear features such as stream number, stream order, mean stream length, stream length, and stream length ratio, areal attributes including elongation ratio, circularity ratio, form factor, constant of channel maintenance, drainage density and drainage texture and relief characteristics such as relief, relief ratio, maximum relief, ruggedness number, relative relief, and length of overland flow. These findings underscore the significance of employing morphometric analysis in watershed assessment, offering a quantitative method for characterizing the surface attributes of a drainage pattern and yielding valuable insights into the topography and runoff dynamics of the region.

Optical coherence tomography (OCT) is a non-invasive imaging technique widely used in ophthalmology for visualizing retinal layers, aiding in early detection and monitoring of retinal diseases. OCT is useful for detecting diseases such as age-related macular degeneration (AMD) and diabetic macular edema (DME), which affect millions of people globally. Over the past decade, the area of application of Artificial Intelligence (AI), particularly Deep Learning (DL), has significantly increased. The number of medical applications is also rising, with solutions from other domains being increasingly applied to OCT. The segmentation of biomarkers is an essential problem that can enhance the quality of retinal disease diagnostics. For 3D OCT scans, AI is beneficial since manual segmentation is very labor-intensive. In this paper, we employ the new SAM 2 and MedSAM 2 for the segmentation of OCT volumes for two open-source datasets, comparing their performance with the traditional U-Net. The model achieved an overall Dice score of 0.913 and 0.902 for macular holes (MH) and intraretinal cysts (IRC) on OIMHS and 0.888 and 0.909 for intraretinal fluid (IRF) and pigment epithelial detachment (PED) on the AROI dataset, respectively.

Semantic segmentation of high-resolution remote sensing images provides detailed and precise feature information, playing a pivotal role in decision-making and analysis in sectors such as water management, agriculture, military, and environmental protection. However, most methods merely combine features from various branches directly, without a mechanism for spatial location feature screening, and treat all extracted features as equally important. To overcome these limitations, we introduce a novel spatially adaptive interaction network (SAINet) for dynamic interaction across different features in remote sensing semantic segmentation task. Specifically, we propose a spatial refined module that leverages local context information to filter spatial locations and extract salient regions. Following this, we introduce an innovative spatial interaction module that uses a spatial adaptive modulation mechanism to dynamically select and allocate spatial position weights. This facilitates interaction between local salient areas and global information, allowing the network to focus more on relevant regions. This flexible approach enables the network to capture more informative features, thereby enhancing segmentation accuracy. Experiments conducted on the DeepGlobe, Vaihingen, and Potsdam public datasets confirm the effectiveness and capability of SAINet. Our code and models will be publicly available

This study introduces a sophisticated neural network structure for segmenting breast tumors. It achieves this by combining a pretrained Vision Transformer (ViT) model with a U-Net framework. The U-Net architecture, commonly employed for biomedical image segmentation, is further enhanced with Depthwise Separable Convolutional Blocks to decrease computational complexity and parameter count, resulting in better efficiency and less overfitting. The Vision Transformer, renowned for its robust feature extraction capabilities utilizing self-attention processes, efficiently captures the overall context within images, surpassing the performance of conventional convolutional networks. By using a pretrained ViT as the encoder in our U-Net model, we take advantage of its extensive feature representations acquired from extensive datasets, resulting in a major enhancement in the model’s ability to generalize and train efficiently. The suggested model has exceptional performance in segmenting breast cancers from medical images, highlighting the advantages of integrating transformer-based encoders with efficient U-Net topologies. This hybrid methodology emphasizes the capabilities of transformers in the field of medical image processing and establishes a new standard for accuracy and efficiency in activities related to tumor segmentation.

Uncontrolled and fast cell proliferation is the cause of brain tumors. Early cancer detection is vitally important in order to save many lives. Brain tumors can be divided into several categories depending on the kind, place of origin, pace of development, and stage of progression; as a result, tumor classification is crucial for targeted therapy. The aim of brain tumor segmentation is to accurately delineate the areas of the brain. A specialist with a thorough understanding of brain illnesses must manually identify the proper type of brain tumor. Additionally, processing a lot of images takes time and is tiresome. Therefore, automatic segmentation and classification techniques are required to speed up and enhance the diagnosis of brain tumors. Tumors can be quickly and safely detected by brain scans using imaging modalities, including computed tomography (CT), magnetic resonance imaging (MRI), and others. Machine learning (ML) and artificial intelligence (AI) have shown promise in the development of algorithms that aid in automatic classification and segmentation utilizing various imaging modalities. This review discussed various types of brain tumors, publicly accessible datasets, enhancement methods, segmentation, feature extraction, classification, machine learning techniques, and deep learning, learning through transfer, for the study of brain tumors.

The role of trees in watershed hydrology is governed by many environmental factors along with their inherent characteristics and not surprisingly has generated into diverse debates in the literature. Herein, this state-of-the-art review provides an opportunity to propose a conceptual model for understanding the role of trees in watershed hydrology and examine the conditions under which they can be an element that increases or decreases water supply in a watershed hydrology. To achieve this goal, this review addressed the interaction of forest cover with climatic conditions, soil types, infiltration, siltation and erosion, water availability, and the diversity of their ecological features. The novelty of the proposed conceptual model highlights that tree species and densities, climate, precipitation, type of aquifer, and topography are important factors affecting the relationships between trees and water availability. This suggests that forests can be used as a nature-based solution for conserving and managing natural resources, including water, soil and air. To sum up, forests can reduce people’s imprint, thanks to their role in improving water and air quality, conserving soil, and other ecosystem services. The outcomes of this study should be valuable for decision-makers when investing in reforestation in a watershed hydrology.

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in e.g. paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78±0.00 on the classification and detection task, and 0.80±0.00 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84±0.00 and 0.86±0.00, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work, and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

With the rapid development of smart phones, tablets and their operative systems, many positioning enabled sensors have been built into these devices. Users can now accurately fix their location according to the function of GPS receivers. For indoor environments, as in the case we are studying, WiFi based positioning is preferred to GPS due to the attenuation or obstruction of signals. This paper deals with the automatic classification of customers in a Sports Shop Center on the basis of their movements around the shop's premises. To achieve this goal, we start by collecting (x,y) coordinates from customers while they visit the store. Consequently, any costumer's path through the shop is formed by a list of coordinates, obtained with a frequency of one measurement per minute. Then, a guess about the full trajectory is constructed and a number of parameters about these trajectories is calculated before performing an Unsupervised Learning Clustering Process. As a result, we can identify several types of customers, and the dynamics of their behavior inside the shop. This information is of great value to the company, to be used both in the long term and also in short periods of time, monitoring the current state of the shop at any moment, identifying different types of situation appearing during restricted periods, or predicting customer flow conditions

Recent advancements in deep learning have spurred the development of numerous novel semantic segmentation models for land cover mapping, showcasing exceptional performance in delineating precise boundaries and producing highly accurate land cover maps. However, to date, no systematic literature review has comprehensively examined semantic segmentation models in the context of land cover mapping. This paper addresses this gap by synthesizing recent advancements in semantic segmentation models for land cover mapping from 2017 to 2023, drawing insights on trends, data sources, model structures, and performance metrics based on a review of 106 extracted articles. Our analysis identifies top journals in the field, including MDPI Remote Sensing, IEEE Journal of Selected Topics in Earth Science, and IEEE Transactions on Geoscience and Remote Sensing, IEEE Geoscience and Remote Sensing Letters, ISPRS Journal Of Photogrammetry And Remote Sensing as the leading journals. We find that research predominantly focuses on land cover, urban areas, precision agriculture, environment, coastal areas, and forests. Geographically, 35.29% of the study areas are located in China, followed by USA (11.76%), France (5.88 %), Spain (4%) and others. Sentinel-2, Sentinel-1, and Landsat satellites emerge as the most commonly used data sources. Benchmark datasets such as ISPRS Vaihingen & Potsdam, LandCover.ai, DeepGlobe, and GID datasets are frequently employed. Model architectures predominantly utilize encoder-decoder, and hybrid convolutional neural network-based structures because of their impressive performances, with limited adoption of transformer-based architectures due to its computational complexity issue, and slow convergence speed. Lastly, this paper highlights existing key research gaps in the field to guide future research directions.

Social network analysis is extensively employed for the examination of relationships and networks among actors across diverse disciplines and thematic research domains. Nevertheless, the utilization of this approach in agriculture and natural resources, particularly pertaining to watershed management, has been relatively limited. The objective of this study is to conduct an analysis of the social interaction and networks of Cidanau Watershed Management (CWM) stakeholders and measure the nodes of units as individuals or organizations in relation to the role and influence of each other through a quantitative approach. The results of the data analysis show that Fkdc has a high degree of centrality and centrality betweenness. This shows that Fkdc has a strong influence and controls CWM network interaction. Conversely, Hs (households) have a low degree of centrality, and centrality betweenness values have a low influence and role in actors’ networks. According to the closeness centrality parameter, it is observed that both Households (Hs) and Universities (Univ) have exhibited the shortest geodesic distance in relation to other stakeholders within the network, thus indicating their highest level of closeness. It means that households and universities had interdependency and were controlled by others. The lowest centrality of Fkdc means that Fkdc has independence of influence and high control access over others. There are four CWM network clusters based on total link strength. Fkdc demonstrates outstanding leadership qualities, enjoys a strong reputation, and possesses a high degree of popularity within the network. Furthermore, Fkdc serves as a positive central node that effectively brings together the interests of all actors, fostering a collective commitment towards shared goals and mutual rewards. In the CWM case, Fkdc is a sustainable watershed organization that acts as a central network body and plays a fundamental role as an intermediary between networks and interactions. Ultimately, with regards to the viewpoint of CWM, the decentralization of watersheds aimed to facilitate wider public engagement by establishing Fkdc as a central network entity and assuming a crucial role as a medium for the dissemination of information, exchange of ideas, and the exertion of influence among its members.

According to the World Meteorological Organization, since 2000, there has been an increase in global flood-related disasters by 134 percent as compared to the two previous decades. Efficient flood risk management strategies necessitate a holistic approach to evaluating flood vulnerabilities and risks. Catastrophic losses can occur when the peak flow values in the rivers in a basin coincide. Therefore, estimating the joint flood risks in a region is vital, especially when frequent occurrences of extreme events are experienced. This study focuses on estimating the joint flood risks due to river flow extremes in the Grand River watershed in Canada. Determining the interdependence of floods at multiple locations using state-of-the-art tools, the associated damage probabilities, and their costs will be beneficial to various stakeholders, such as the insurance industry, the disaster management sector, and most importantly, the public.

This study presents results of the sediment yield Watershed of Ribeirão do Pinhal, in the city of Limeira, São Paulo, conducted under three different scenarios of the land use: 1 – land use in 2008, 2 – with reforested protection areas, 3 – the increase sugarcane's areas over grassland and citrus areas. The Soil and Water Assessment Tool (SWAT) was used as a hydro-sedimentological modeling tool to simulate these scenarios. This watershed was divided into five sub-watersheds according to the prevalent use, and adjustments were made in soils database parameters and cultures that are in SWAT, to adapt it to the Brazilian reality. Was used climatological data of eight years (2007-2014) for this modeling. Different sediment yield could be noted in the different types of land use, sub-watersheds and scenarios. The uses that presented higher sediment yield, in ascending order, were: natural vegetation, sugarcane, citrus, annual crop e grassland. Sub-watershed number 2 had the highest sediment yield (~10Mg.ha^-1), while the sub-watershed 5, the lowest (5.51Mg.ha^-1). This remained in the three scenarios. Overall, scenario 2 had the lowest sediment yield (7.74Mg.ha^-1). Scenario 1 had 8.37 Mg.ha^-1 and scenario 3, 8.58Mg.ha^-1. SWAT was considered efficient to simulate the sediment yield by scenarios and by use, combining different thematic and tabular data when performing the necessary adjustments on their original database.

The risk related to embankment dam breaches needs to be evaluated in order to prepare emergency action plans. The physical and hydrodynamic parameters of the flood wave generated from dam-failure event correspond to various breach parameters such as width, slope and formation time. This study aimed to simulate dam-breach failure scenario of Yabous dam (NE Algeria) and analyze its influence on areas (urban and natural environments) downstream the dam. The simulation was completed using the sensitivity analysis method in order to assess the impact of breach parameters on the dam-break scenario. The propagation of flood wave associated to dam-break was simulated using the one-dimensional HEC-RAS hydraulic model. This study ap-plied a sensitivity analysis of three breach parameters (slope, width, and formation time) in five sites selected downstream the embankment dam. The simulation showed that the maximum flow of the flood wave recorded at the level of the breach was 8768 m3/s, which gradually attenuated along the river course to reach 1579.2m3/s at about 8.5km downstream the dam. This study estab-lished the map of flood-prone areas that illustrated zones threatened with the flooding wave trig-gered by the dam failure due to extreme rainfall events. The sensitivity analysis showed that flood wave flow, height and width revealed positive and similar changes for the increase in adjustments (±25% and ±50%) of breach width and slope in the 5 sites. However, flood wave parameters of breach formation time showed significant trends that changed in the opposite direction compared to breach slope and width.

The change in both streamflow and baseflow in urban catchments has received significant attention in the latest decades as a result of their drastic variability. In this research, effects of climate variation and dynamics of land use are measured separately and in combination on streamflow and baseflow in the Little Eagle Creek (LEC) watershed (Indianapolis, Indiana). These effects are examined using land use maps, statistical tests, and hydrological modeling. Transition matrix analysis was used to investigate the change in land use between 1992 and 2011. Temporal trends and changes in meteorological data were evaluated from 1980-2017 using the Mann-Kendall test. Changes in streamflow and baseflow were assessed using the Soil and Water Assessment Tool (SWAT) hydrological model using multiple scenarios that varied in land use and climate change. Evaluation of the model outputs showed streamflow and baseflow in LEC are well represented using SWAT; however, comparing the calibration and validation period showed SWAT performs better for the calibration. During 1992-2011, roughly 30% of the watershed experienced change, typically cultivated agricultural areas became urbanized. Baseflow is significantly affected by the observed urbanization; however, the combination of land and climate variability has a larger effect on the baseflow in LEC. Generally, the variability in the baseflow and streamflow appears to be heavily driven by the response to climate change in comparison to variability due to altered land use. The results reported herein expand the current understanding of variation in hydrological components, and provides useful information for management planning regarding water resources, as well as water and soil conservation in urban watersheds in Indiana and beyond.

Evaluating soil quality across various altitudinal gradients, both with and without vegetative cover, is crucial for the proper functioning of soil and optimal crop growth, thereby contributing to the sustainability of agroecosystems. Although the altitudinal gradient significantly influences soil quality, the ability to predict this quality, expressed through an index, in soils with and without vegetative cover, is still insufficiently explored. This study aimed to assess soil quality in the Jun Jun micro-watershed, located in the Tungurahua region, Ecuador. To achieve this objective, three categories of altitudinal gradients were selected: less than 2800 meters above sea level (masl), between 2800 and 2900 masl, and greater than 2900 masl. A total of 24 soil samples were collected in the mentioned gradients, considering both areas with and without vegetative cover. The indicators used included chemical and biological parameters such as soil organic carbon (OC), earthworm density (WD), earthworm biomass (WB), organic matter (OM), pH, total nitrogen (TN), and organic carbon (OC). The results revealed that in areas with altitudinal gradients below 2800 masl, soil quality index values were higher compared to other altitudes. In vegetated areas, a decrease in index values was observed as the altitudinal gradient increased, indicating a deterioration in soil quality with altitude. These findings are significant in providing a quantitative assessment of the effects of altitudinal gradient and vegetative cover influence on soil quality.

The use of strobilurin fungicides in agriculture has increased steadily during the past 25 years, and although strobilurins have minimal water solubility, they regularly appear in surface waters, at times in concentrations approaching toxic levels for aquatic life. The present study examined concentrations of strobilurin fungicides in designated trout streams draining an agricultural watershed in southeastern Minnesota, USA, where fungicides may have contributed to a recent fish kill. Water samples (n = 131) were analyzed for the presence of five different strobilurin fungicides (azoxystrobin, fluoxastrobin, picoxystrobin, pyraclostrobin, trifloxystrobin). Samples were collected via grab and automated sampling during baseflow and stormflow events throughout an entire crop growing season from sites on each of three forks of the Whitewater River. Detection frequencies for the five strobilurins ranged from 44 to 82%. Fluoxastrobin and pyraclostrobin concentrations were above known toxic levels in 3% and 15% of total samples analyzed, respectively. The highest concentrations were detected in mid-summer (mid-June to mid-August) samples, coincident with likely strobilurin applications. Lower concentrations were present in water samples collected during the non-application periods in spring and fall, suggesting groundwater-stream interactions or steady leaching of fungicides from watershed soils or stream sediments. Further study is required to determine strobilurin concentrations in sediments, soils, and groundwater. Better tracking and guidance regarding strobilurin use is necessary to adequately protect aquatic life as fungicide use continues to increase.

Water, soil/sediment, and 36 fish samples were collected at three major sites along Flint Creek in 2015-2016 and analyzed for total organic carbon (TOC), dissolved organic carbon (DOC), total mercury (tHg), and other water quality indicators. This study was a follow-up to a 2012 study that revealed elevated tHg levels in fish, resulting in a public health advisory. This study revealed tHg concentrations in water below the detection limit (0.0002 ppm); while, tHG in soil/sediment ranged from < 0.0133 ppm to 0.0682 ppm dry weight. No temporal trends existed, but tHG tended to increase with TOC. Mercury levels in sediment were below the threshold effects level suggested as a preliminary screening level by the National Oceanic and Atmospheric Administration (acute = 1.4, chronic = 0.77 ppb). In summary, tHg levels were low; posing little risk to drinking water. Soil/sediment levels were generally higher and could pose risk to aquatic species.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: describe briefly the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article, it must not contain results which are not presented and substantiated in the main text and should not exaggerate the main conclusions.

Anomaly detection and segmentation aim at distinguishing abnormal images from normal images and further localizing the anomalous regions. Feature reconstruction based method has become one of the mainstream methods for this task. This kind of method has two assumptions: (1) The features extracted by neural network is a good representation of the image. (2) The autoencoder solely trained on the features of normal images cannot reconstruct the features of anomalous regions well. But these two assumptions are hard to meet. In this paper, we propose a new anomaly segmentation method based on feature reconstruction. Our approach mainly consists of two parts: (1) We use a pretrained vision transformer (ViT) to extract the features of the input image. (2) We design a self-attention autoencoder to reconstruct the features. We regard that the self-attention operation which has a global receptive field is beneficial to the methods based on feature reconstruction both in feature extraction and reconstruction. The experiments show that our method outperforms the state-of-the-art approaches for anomaly segmentation on the MVTec dataset. It is both effective and time-efficient.

The problem of event detection in general noisy signals arises in many applications; usually, either a functional form for the event is available, or a previous annotated sample with instances of the event that can be used to train a classification algorithm. There are situations, however, where neither functional forms nor annotated samples are available; then it is necessary to apply other strategies to separate and characterize events. In this work, we analyze 15 minute-long samples of an acoustic signal, and are interested in separating sections, or segments, of the signal which are likely to contain significative events. For that, we apply a sequential algorithm with the only assumption that an event alters the energy of the signal. The algorithm is entirely based on Bayesian methods.

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer’s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

Pepper leaf segmentation plays a crucial role in monitoring pepper leaf diseases in various backgrounds and ensuring the healthy growth of peppers. However, existing transformer-based segmentation methods suffer from computational inefficiency, excessive parameterization, and limited utilization of edge information. To tackle these challenges, we propose an adaptive multi-scale MLP framework, named AMS-MLP, which combines the multi-path aggregation module (MPAM) and the multi-scale context relation mask module (MCRD) to refine the object boundaries in pepper leaf segmentation. AMS-MLP consists of an encoder-based network, an adaptive multi-scale MLP (AM-MLP) module, and a decoder network. In the encoder network, the MPAM module effectively fuses five-scale features to generate a single-channel mask, improving the accuracy of pepper leaf boundary extraction. The AM-MLP module divides the input features into two branches: the global multi-scale MLP branch captures long-range dependencies between image information, while the local multi-scale MLP branch focuses on extracting local feature maps. Adaptive attention mechanism is designed to dynamically adjust the weights of global and local features. The decoder network incorporates the MCRD module into the convolutional layer, enhancing the extraction of boundary features. To verify the performance of the proposed method, we conducted extensive experiments on three pepper leaf datasets with different backgrounds. The results demonstrate mIoU scores of 97.39%, 96.91%, and 97.91%, as well as F1 scores of 98.29%, 97.86%, and 98.51%, respectively. Comparative analysis with U-Net and state-of-the-art models reveals that the proposed method dramatically improves the accuracy and efficiency of pepper leaf image segmentation.

The Storm Water Management Model (SWMM) was used to evaluate the impact of urbanization, climate change, and implementation of Low Impact Developments (LIDs) at the Mahabad Dam watershed, Iran. Several scenarios of urbanization, with and without climate change impacts, in different locations were defined, including near outlet, middle, far end, and whole watershed. Climate change was considered to change the intensity of rainfall and increase evaporation. Vegetative swales were implemented as LIDs to evaluate their applicability to reduce pollutant loads. Digital Elevation Model (DEM) of the area was input into ArcGIS, and the watershed was delineated using the ArcSWAT extension to identify topographic features. Water quality properties were defined in the software, and each scenario was run for a twelve-hour simulation. The results indicated that urbanization affects the imperviousness of sub-catchments, and location of urbanization affects the amount and timing of runoff and pollutant yields. Fifty-percent urbanization near the watershed outlet resulted in 23.1% and 27.4% increases in runoff and pollutant loads, respectively. Fifty-percent urbanization in the middle resulted in 28.8% and 35.4% increases in runoff and pollutant loads; and, at the far end, 23.1% and 3.9% increases in runoff and pollutant loads were the result; Fifty-percent urbanizing the whole watershed gave 58.6% and 66.3% increases in runoff and pollutant loads, respectively; Under climate change scenarios (higher intensity, shorter duration rainfall) peaks occurred earlier. Moreover, results showed LIDs decreased pollution loads up to 25%.

Purpose: Carotid intraplaque hemorrhage (IPH) increases risk of territorial cerebral ischemic events, but different sequences or criteria have been used to diagnose or quantify carotid IPH. The purpose of this study was to compare manual segmentation and semi-automatic segmentation for quantification of carotid IPH on magnetization-prepared rapid acquisition with gradient-echo (MPRAGE) sequences. Methods: Forty patients with 16–79% carotid stenosis and IPH on MPRAGE sequences were reviewed by two trained radiologists with more than five years of specialized experience in carotid plaque characterization with carotid plaque MRI. Initially, the radiologists manually viewed the IPH based on the MPRAGE sequence. IPH volume was then measured by three different semi-automatic methods, with high signal intensity 150%, 175%, and 200%, respectively, above that of adjacent muscle on the MPRAGE sequence. Agreement on measurements between manual segmentation and semi-automatic segmentation was assessed using the intraclass correlation coefficient (ICC). Results: There was near-perfect agreement between manual segmentation and the 150% and 175% criteria for semi-automatic segmentation in quantification of IPH volume. The ICC of each semi-automatic segmentation were as follows: 150% criteria: 0.861, 175% criteria: 0.809, 200% criteria: 0.491. The ICC value of manual vs. 150% criteria and manual vs. 175% criteria were significantly better than the manual vs. 200% criteria (p < 0.001). Conclusions: The ICC of 150% and 175% criteria for semi-automatic segmentation are more reliable for quantification of IPH volume. Semi-automatic classification tools may be beneficial in large-scale multicenter studies by reducing image analysis time and avoiding bias between human reviewers.

This study investigates the capabilities of high-resolution Sentinel-2 observations and deep learning (DL) segmentation models, specifically convolutional neural networks (CNNs), for accurate mapping of small and fragmented agricultural burn areas in Punjab, India. Initially, the model was trained using ICNF burn area data from Portugal to capture large fire and burn area delineation, achieving moderate accuracy. Subsequent fine-tuning using annotated data from Punjab improved the model’s ability to detect small burn patches, demonstrating higher accuracy and precision than the baseline Normalised Burn Ratio (NBR) Index method. On-ground validation using buffer zone analysis and crop field images confirms the DL approach effectiveness. Cloud interference and temporal gaps in satellite data posed some challenges. Despite these limitations, the study highlights the methodological advancements and potential of using DL models for small burn area detection in agricultural settings. The model achieved overall testing accuracy of 0.64 in Dice score assessment. This report presents a promising approach for improved mapping of the burn area, which might engender better estimation of emissions and the management practices in regions with little available ground truth data.

Land cover mapping, essential for understanding global land use patterns, relies on satellite imagery for monitoring changes, assessing ecosystem health, and supporting conservation ef- forts. However, significant challenges remain in managing large, complex satellite imagery datasets, acquiring specialized datasets due to high costs and labor intensity, and a lack of comparative studies for optimal deep learning model selection. Additionally, a scarcity of aerial datasets specifically tailored for agricultural areas exists. This study addresses these gaps by presenting a method for semantic segmentations of land covers in agricultural areas using satellite images and deep learning models with pre-trained backbones. We introduce an efficient methodology for preparing semantic segmentation datasets and contribute the "Land Cover Aerial Imagery" (LICAID) dataset for semantic segmentation. The study focuses on the Franciacorta area, Lombardy Region, leveraging the rich diversity of the dataset to effectively train and evaluate the models. We conduct a comparative study, employing cutting-edge deep learning-based segmentation models (U-Net, SegNet, DeepLabV3) with various pre-trained backbones (ResNet, Inception, DenseNet, EfficientNet) on our dataset acquired from Google Earth Pro. Through meticulous data acquisition, preprocessing, model selection, and evaluation, we demonstrate the effectiveness of these techniques in accurately delineating land cover classes. Integrating pre-trained feature extraction networks significantly improves performance across various metrics. Additionally, addressing challenges such as data availability, computational resources, and model interpret-ability is essential for advancing the field of remote sensing and supporting sustainable environmental stewardship worldwide.

Sustained water management requires quantitative information and the knowledge of spatiotemporal dynamics of hydrological system within the basin. This can be achieved through the research. Several studies have investigated both surface water and groundwater in Beterou catchment. However, there are few published papers on the application of the SWAT modeling in Beterou catchment. The objective of this study was to evaluate the performance of SWAT to simulate the water balance within the watershed. The inputs data consist of digital elevation model, land use maps, soil map, climatic data and discharge records. The model was calibrated and validated using the Sequential Uncertainty Fitting (SUFI2) approach. The calibrated started from 1989 to 2006 with four years warming up period (1985-1988); and validation was from 2007 to 2020. The goodness of the model was assessed using five indices, i.e., Nash–Sutcliffe efficiency (NSE), the ratio of the root means square error to the standard deviation of measured data (RSR), percent bias (PBIAS), the coefficient of determination (R²), and Kling Gupta efficiency (KGE). Results showed that SWAT model successfully simulated river flow in Beterou catchment with NSE = 0.79, R2 = 0.80 and KGE= 0.83 for the calibration process against validation process that provides NSE = 0.78, R2 = 0.78 and KGE= 0.85 using site-based streamflow data. The relative error (PBIAS) ranges from -12.2% to 3.1%. The parameters runoff curve number (CN2), Moist Bulk Density (SOL_BD), Base Flow Alpha Factor (ALPHA_BF), and the available water capacity of the soil layer (SOL_AWC) were the most sensitive parameter. The study provides further research with uncertainty analysis and recommendations for model improvement and provision of an efficient means to improve rainfall and discharges measurement data.

This paper proposes a method to utilize weather and land cover models to generate future environmental scenarios, and presents the watershed models to simulate the hydrological impact on watershed-scale hydrology. The Weather Generator model and General Circulation Model were applied to produce rainfall and local temperature under different climate conditions, and the Conservation and Land Use and its Effects model was incorporated to simulate future land cover variability. The circumstances of future climate and land cover changes were used as inputs to drive the HEC-HMS rainfall runoff model for obtaining surface runoff in a mountainous area. The WASH123D model was then utilized for the entire watershed simulation. Modeling results were then examined to discuss hydrological impacts on three different time periods: near future (2020-2039), future (2050-2069), and distant future (2080-2099). The Fengshan Creek basin in northern Taiwan was selected as study site. Simulations results indicated that the influence of climate change revealed more relevant effects when compared to local land cover changes. The ground water levels tended to diminish as the land cover area changed. In addition, both river and groundwater levels reveal that it is drier in dry season and wetter in wet season in future.

One of the most leading causes of death worldwide is Colorectal cancer(CRC). Polyp segmentation is the most important detected measure for preventing CRC. However, there is still a missing rate for diminutive polyps and multiple ones. In order to solve the phenomenon, we propose to introduce auxiliary attention module(AAM) that can enhance the learning of features related to multiple and diminutive polyps by focusing more on the located and detailed information. Meanwhile, we design to decrease missed rate of multiple and diminutive polyps by implementing an area adaptive loss(AAL) which adapts the weight according to the area and the number of polyps. Our proposed novel AAM and AAL concentrates on training with hard examples and localized information. To evaluate the effectiveness and generalization ability of our proposed model, We utilize three different datasets of variable sizes and a cross dataset. Our proposed method achieves the best results on the Kvasir-SEG dataset, the CVC-ClinicDB dataset and the cross dataset, particularly for the Kvasir-Sessile dataset consisting of small,flat and diminutive polyps. Extensive experimental results show that our proposed DoubleAANet surpass the performance of all existing state-of-the-art segmentation methods.

In the realm of computer vision, semantic segmentation is the task of recognizing objects in images at the pixel level. This is done by performing a classification of each pixel. The task is complex and requires sophisticated skills and knowledge about the context to identify objects’ boundaries. The importance of semantic segmentation in many domains is undisputed. In medical diagnostics, it simplifies the early detection of pathologies, thus mitigating the possible consequences. In this work, we provide a review of the literature on deep ensemble learning models for polyp segmentation and we develop new ensembles based on convolutional neural networks and transformers. The development of an effective ensemble entails ensuring diversity between its components. To this end, we combine different models (HarDNet-MSEG, Polyp-PVT, and HSNet) trained with different data augmentation techniques, optimization methods, and learning rates, which we experimentally demonstrate to be useful to form a better ensemble. Most importantly, we introduce a new method to obtain the segmentation mask which is more suitable for combining transformers in an ensemble. In our extensive experimental evaluation, the proposed ensembles exhibit state-of-the-art performance.

Current bridge inspection practices rely on paper-based data acquisition, digitization, and multiple conversions in between incompatible formats to facilitate data exchange. This practice is time-consuming, error-prone, cumbersome, and leads to information loss. One aim for future inspection procedures is to have a fully digitized workflow that achieves loss-free data exchange, which lowers costs and offers higher efficiency. On the one hand, existing studies proposed methods to automatize data acquisition and visualization for inspections. These studies lack an open standard to make the gathered data available for other processes. On the other hand, several studies discuss data structures for exchanging damage information through out different stakeholders. However, those studies do not cover the process of automatic data acquisition and transfer. This study focused on a framework that incorporates automatic damage data acquisition, transfer, and a damage information model for data exchange. This enables inspectors to use damage data for subsequent analyses and simulations. The proposed framework shows the potentials for a comprehensive damage information model and related (semi-)automatic data acquisition and processing.

Flooding and overflows are recurring problems in several Brazilian cities, which usually undergo disorderly development. Their causes vary from increased impervious surface areas, deficiency/inefficiency of drainage structures and their maintenance, siltation of rivers, channel obstructions, and climatic factors. This situation is aggravated in the major cities. The Anhangabau watershed lies in the central portion of the city of Sao Paulo – Brazil and covers a drainage area of 5.4 km². The region is highly urbanized and crossed by a major north-south road connection. During heavy rain events, portions of this interconnection passage become compromised, disrupting the flow of vehicles, creating a chaotic situation for the population, as well as losses to the national economy. Observed rainfall records and an existing IDF (intensity duration frequency) curve for the region are used to obtain design storms. To account for climate change, a well know procedure, the equidistance quantile matching method for updating IDF curves under climate change, was applied to the existing historical data. Several different global climate models (GCM) and one regional model were applied to obtain and update rainfall design storm. The GCMs and future scenarios used were from the IPCC Assessment Report 5 (AR5) and two future projections: RCP (representative concentration pathway) 4.5 and 8.5. Alternatives previously proposed to solve to flooding issue are briefly reviewed. On one of the latest studies [1], a few modern concepts of water resources management are presented, and the linear retention measure was found to offer higher potential to mitigate the flooding problem in the lower valley of the watershed. Therefore, this alternative was used to evaluate different design storms scenarios combined with return periods of 25 and 100-years as well as the updated IDF under climate change for RCP 4.5 and RCP 8.5. To model the complex network, representing both road and drainage systems and their interconnections, PCSWMM/SWMM software was applied. Results are presented as flooding maps and show the impacts of the proposed linear retention measure based on the existing IDF curves and the updated IDF curves under climate change for two different drainage system conditions, current and improved with the use of linear retention reservoirs. Results show that the prosed changes on the drainage system help reduce the risk and damage to flooding. The climate change scenarios, however, impose a significant threat and need immediate attention from city planners and stakeholders.

Identification and segmentation of rock particles is very important in geology, mining, engineering construction, and environmental monitoring. Traditional methods for recognizing the rock particle characteristics are time-consuming, labor-intensive, and limited by the geographical scope of the sampling sites, which makes it more difficult to represent the spatial distribution of the rock particles accurately. Recent advancements in deep learning techniques offer promising solutions to automate this process. This study aims at utilizing state-of-the-art (SOTA) Mask R-CNN deep learning algorithm from the Detectron2 framework, to capture global features of rocks that will enable the recognition of rock particles more efficiently, just from having the rock images. These images are subject to image processing techniques such as a Gaussian filter, to denoise and smoothen the image, and an Illumination Adaptive Transformer (IAT) framework, to adjust the lighting exposure; all of which add to improve the quality of the image dataset. Afterward, the Mask R-CNN and Detectron2 models are utilized in training the images using transfer learning. Experimental results from evaluating the performance of the proposed algorithms showcase the effectiveness of the approach, thereby highlighting its potential to revolutionize rock particle segmentation across various domains.

Nowadays, semantic segmentation is increasingly used in exploration by underwater robots, for example in autonomous navigation, so that the robot can recognise the nature and elements of its environment during the mission and act according to this classification to avoid collisions. Other applications can be found in the search for archaeological artefacts, in the inspection of underwater structures or in species monitoring. Therefore, it is necessary to try to improve the performance in these tasks as much as possible. To this end, we compare some methods for improving image quality and for data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementations and the SUIM dataset with 8 common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The single result shows that there are 5 classes with an IoU value above 60% and only one class with an IoU value below 30%, which is a more reliable result and easier to use in real contexts.

Teeth segmentation plays a pivotal role in dental diagnosis, treatment, planning, and the development of computer-aided dental systems. It enables precise identification and analysis of dental structures, aiding in detecting dental abnormalities, measuring tooth dimensions, and assessing oral health conditions. Accurate teeth segmentation also facilitates the automation of dental workflows, leading to improved efficiency and reduced human error. Artificial Intelligence (AI) has witnessed rapid advancements, with various approaches developed or enhanced. While Convolutional Neural Networks (CNNs) have been widely used in medical image segmentation, the U-Net architecture has emerged as a standout performer due to its exceptional segmentation capabilities. This paper presents a proof of concept for the Attention U-Net architecture, as previously used in [1], applied to teeth segmentation. The study demonstrates the superior performance of this network in accurately segmenting teeth using a newly available benchmark dataset called Tufts Dental X-Ray Dataset. When trained and tested on 10-fold cross-validation, the model achieved an average dice coefficient of 95.01%, intersection over union of 90.6%, and pixel accuracy of 98.82%. These scores surpass those of all other networks implemented on the same dataset. By leveraging the Attention U-Net architecture, our research showcases the potential of advanced AI techniques in dental radiography. The findings contribute to the ongoing efforts to develop automated systems to assist dental professionals in their clinical practice.

Dissolved calcium (Ca2+) concentrations in freshwater ecosystems are of growing concern as increasing levels have been implicated in altering the environmental conditions and biodiversity. Elevated Ca2+ levels and sporadic re-emergence and disappearance of invasive zebra mussels in Kentucky Lake in recent years served as a motivation for this study. The objective of this study was to determine Ca2+ spatial and temporal patterns in Kentucky Lake, selected tributary streams, and the Ohio River during and following a zebra mussel invasion. Over 1000 water samples were collected and analysed for dissolved calcium during 2018-2022. Approved analytical methods were followed for sampling and measuring dissolved calcium levels. Results revealed significant spatial and temporal patterns. Kentucky Lake Ca2+ levels varied between 15-25 mg/L depending on the sampling location and month/year. Kentucky Lake channel sites exhibited comparably higher concentrations of Ca 2+ than did most embayment and/or stream sites, indicating that tributary streams did not serve as primary sources of calcium to the lake. Dissolved calcium levels at main lake sites exceeded the threshold for zebra mussel growth and reproduction in 2018 during the time when zebra mussels were present. Calcium in lake water samples collected from 2019 through 2022 was at or just below the threshold. Temporal trend data showed a gradual increase in Ca2+ in Kentucky Lake throughout the study period but remaining at or below the threshold level considered critical for the zebra mussels’ reproduction and development. Calcium levels in the Ohio River site at Paducah were similar to Kentucky Lake reflecting the predominance of Tennessee River water, while levels at the Brookport site were consistent with values known to support zebra mussel populations. The elevated calcium levels in Kentucky Lake waters during the late winter and early spring months may be due to natural sources (mineral weathering) as well as human activities in the Tennessee River basin. This study emphasizes the need for continued calcium monitoring in the watershed to determine the potential for future zebra mussel outbreaks and potential influences on the lake ecosystem and its functions.

Agricultural activities within watersheds can have negative effects on river ecosystems, but numerous conservation practices can be implemented that reduce soil erosion, increase water infiltration, slow runoff, and improve soil quality. Our study focused on analyzing overall stream health (instream and riparian physical, instream biological) at 56 stream sites within an agricultural watershed (83,000 hectares, 70% croplands and rangelands) with a 30+-year history of targeted conservation practices to protect local water resources of importance for tourism and recreation. After implementation of >900 best management practices (BMPs) over the last 20 years in the study subwatersheds, only 20% of the stream sites examined exhibited good stream health and 40% were in poor condition, based on a combination of instream and riparian factors and aquatic community integrity. Time since implementation, location, and total coverage of BMPs within the relatively large subwatersheds all may have contributed to the apparent limited effectiveness of these conservation management practices toward producing observable improvements in stream health to date. Many indicators of stream health (e.g., fine sediments, sediment embeddedness, fish biotic integrity) differed significantly among subwatersheds, but those differences could not be explained by differences in numbers or coverages of BMPs in those subwatersheds. Longitudinal stream health patterns were similar among subwatersheds (moderate health in headwaters, poor in mid-reaches, good in lower reaches), likely due, in part, to similarities in locations of spring discharges and channel instability. New rules protecting stream riparia, maintenance of existing BMPs, and future BMPs targeting remaining problem areas should lead to improving stream health in this large watershed.

Human activities mostly impact the trend and direction of surface water, groundwater, and other river basin resources in the watershed in Africa. Human activities influence river flows and the water quality at both highlands and lowlands. A watershed is indeed a conserved area of land that collects rain and snow and empties or penetrates into ground water sources. The act of managing the activities around the watershed is the Integrated Watershed Management while considering the social, economic, and environmental issues, as well as community interests to manage water resources sustainably. These watersheds, river basins, and groundwater resources provide important services for communities and biodiversity. This paper reveals that the best way to protect groundwater resources is on a watershed basis using IWM. This technique enables us to handle a variety of concerns and objectives while also allowing us to plan in a complicated and uncertain environment. IWM involves cooperation and participation from a wide range of community interests and water users, including municipalities, companies, people, agencies, and landowners, for stakeholders' input to be successful. All of the strategies and plans are produced concerning one another, as well as the overall conditions of the watershed, local land uses, and specific issues.

Wildfires have impacted thousands of acres of forests in Arizona and New Mexico in recent years. The extensive damage has been partially attributed to the current forest condition where many once open stands now consist of dense stands of younger, unhealthy trees and buildups of forest fuels. In Arizona, land managers and community organizations developed the Four Forests Restoration Initiative (4FRI) to attempt to rectify the situation by thinning the forest while protecting wildlife and watershed resources. Integrated resource information and research are particularly important today with society’s increased demands for high quality water, healthy forests, sound fire management, and viable wildlife populations. However, many managers are not familiar with previous integrated watershed research in the Southwest that could provide a strong basis for current management decisions or as a basis for future research. New and modified prescriptions to manage the Southwest’s forest resources are vital to answer the threats of wildfires and insect infestations. Integrated forest resource management is necessary to meet the diverse needs of society and the land. The 4FRI plan raised many questions about the effects of silvicultural prescriptions on tree, wildlife, and water resources. The Beaver Creek, Thomas Creek, and Castle Creek watershed experiments all had goals of evaluating integrated resource management options and of providing managers and scientists with useful management information. Much of the knowledge gained in these programs can provide forest managers with a better, more holistic basis for future integrated management of the Southwest USA’s forests and woodlands. This paper reviews research on three watershed areas in Arizona where integrated resource management was successful.

Coffee is one of the most valuable agricultural products worldwide, and it is crucial to have efficient tools to obtain reliable information about production. This study aims to estimate coffee plantation production using segmentation and deep learning techniques in RGB images. Photographs of coffee plants were taken in Tabaconas, San Ignacio-Cajamarca, to create a dataset of crops during the harvest stage. The images were segmented to detect coffee fruits. A deep learning method was developed with YOLOv5 to detect the fruits and OpenCV to count them. The results showed that YOLOv5 achieved an accuracy of 97.25%, a recall of 95.77%, and an F1-Score of 96.37%, demonstrating high reliability in detecting coffee fruits. The average detection time per image was 17.9 seconds. The metrics were evaluated using a confusion matrix, highlighting the model's good performance. In conclusion, segmentation and deep learning techniques, along with counting algorithms developed with OpenCV, proved effective for estimating coffee production. This approach provides a valuable tool for farmers, improving crop management and facilitating decision-making in precision agriculture.

Deep learning is widely used in image segmentation, effectively identifying crops and weeds and contributing to the reduction of herbicide use. Traditional methods of applying pesticides over large areas are inefficient in dealing with weeds as needed, leading to massive waste of pesticides, high-cost production, and serious environmental pollution. This affects crop yield and quality. Although weed recognition using conventional deep learning methods has evolved over time, there are still challenges in weed extraction, detection, and segmentation. Accurate recognition and detection of weeds are essential prerequisites for implementing variable spraying. This paper proposes a semantic segmentation method based on UNet++ for complex environments where accurate identification of plants and weeds is challenging, targeting weeds in sugar beets, peas, and rice. An attention module is integrated into the upsampling process of UNet++, and UNet++ is used as a backbone network to effectively integrate multi-scale information, efficiently suppressing external noise interference. The UNet++ model with an integrated attention mechanism module achieves higher IOU than the general UNet++ model used in medical image analysis. This method effectively detects crops and weeds in complex backgrounds, providing reference material for the accurate application of robotic herbicides.

Iberian ham, a traditional Spanish meat product, is renowned for its unique nutritional and sensory attributes, garnering widespread appreciation both domestically and internationally [1]. It is one of the most outstanding Spanish gastronomic treasures, with very special nutritional and sensory properties that make it highly appreciated throughout the world [2]. Recent trends indicate a notable surge in its consumption, a pattern projected to persist [3]. For an enhanced online shopping experience, understanding the specific characteristics and requirements of various consumer segments is crucial. This study aims to scrutinize national Iberian ham consumption patterns and, through survey methodologies, discern the preferences and needs of online consumers purchasing whole Iberian hams. The subsequent cluster analysis will empower suppliers with insights to pinpoint business prospects and craft segment-specific online marketing strategies.

Lesion studies are crucial in establishing brain-behavior relationships, and accurately segmenting the lesion represents the first step in achieving this. Manual lesion segmentation is the gold standard for chronic strokes. However, it is labor-intensive, subject to bias, and limits sample size. Therefore, our objective is to develop an automatic segmentation algorithm for chronic stroke lesions on T1-weighted MR images. Methods: To train our model, we utilized an open-source dataset: ATLAS v2.0 (Anatomical Tracings of Lesions After Stroke). We partitioned the dataset of 655 T1 images with manual segmentation labels into five subsets and performed a 5-fold cross-validation to avoid overfitting of the model. We used a deep neural network (DNN) architecture for model training. Results: To evaluate the model performance, we used three metrics that pertain to diverse aspects of volumetric segmentation including shape, location, and size. The Dice similarity coefficient (DSC) compares the spatial overlap between manual and machine segmentation. The average DSC was 0.65 (0.61- 0.67; 95% bootstrapped CI). Average symmetric surface distance (ASSD) measures contour distances between the two segmentations. ASSD between manual and automatic segmentation was 12mm. Finally, we compared the total lesion volumes and the Pearson correlation coefficient (ρ) between the manual and automatically segmented lesion volumes, which was 0.97(p-value &lt; 0.001). Conclusions: We present the first automated segmentation model trained on a large multicentric dataset. This model will enable automated on-demand processing of MRI scans and quantitative chronic stroke lesion assessment.

Lung cancer is a deadly disease if not diagnosed in its early stages. However, early detection of lung cancer is a challenging task due to the shape and size of its nodules. Radiologists need support from automated tools for precise opinion. Automated detection of the affected lungs nodule is difficult because of the shape similarity among healthy tissues. Over the years, several expert systems have been developed that help radiologists to diagnose lung cancer. In this article, we propose a framework to precisely detect lungs cancer by classifying it between benign and malignant nodules. The framework is tested using the subset of the publicly available at the Lung Image Database Consortium image collection (LIDC-IDRI). Multiple techniques including filtering and noise removing are applied for pre-processing. Subsequently, the OTSU and the semantic segmentation are used to accurately detect the unhealthy lungs nodules. In total, 13 nodules features were extracted using Principal Components Analysis (PCA) algorithm. Four optimal features are selected based on the classification performance. In the classification phase, 9 different classifiers are used along with two types of validation schemes i.e. train test holdout validation with 70-30 data split and 10 fold cross-validation. Our experiments show that the proposed system provides 99.23\% accuracy using logic boost classifier.

This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Hus{\o}y were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques.

Land use land cover (LULC) changes are highly pronounced in African countries, as they are characterized by an agriculture-based economy and a rapidly growing population. Understanding how land use/cover change (LULCC) influence watershed hydrology will enable local governments and policymakers to formulate and implement effective and appropriate response strategies to minimize the undesirable effects of future land use/cover change or modification and sustain the local socio-economic situation. The hydrological response of the Ethiopia Fincha’a watershed to LULCC happened during the last 30 years was investigated comparing the situation in three reference years: 1994, 2004 and 2018. The information was derived from Landsat sensors, respectively Landsat 5 TM, Landsat 7 ETM and Landsat 8 OLI/TIRS. The various LULC classes were derived via ArcGIS using a supervised classification system, and the accuracy assessment was done using confusion matrixes. For all the years investigated the overall accuracies and the kappa coefficients were higher than 80%, with 2018 as the more accurate year. The analysis of LULCC revealed that forest decreased by 19.99% between the years 1994-2004, and it decreased by 11.85% in the following period 2004-2018. Such decline in areas covered by forest is correlated to an expansion of cultivated land by 16.4% and 10.81%, respectively. After having evaluated the LULCC at the basin scale, the watershed was divided into 18 sub-watersheds, which contained 176 Hydrologic Response Units (HRUs), having a specific LULC. Accounting for such a detailed subdivision of the Fincha’a watershed, the SWAT model was firstly calibrated and validated on past data, and then applied to infer information on the hydrological response of each HRU on LULCC. The modelling results pointed out a general increase of average water flow, both during dry and wet periods, as a consequence of a shift of land coverage from forest and grass towards settlements and build-up areas. The present analysis pointed out the need of accounting for past and future LULCC in modelling the hydrological responses of rivers at the watershed scale.

Despite increased awareness of and attention to the need for sustainable agriculture, fertilizers and compost application in excess of crop requirements remain common agricultural practices in South Korea, causing eutrophication of freshwater and coastal ecosystems. In this study, a phosphorus (P) budget was developed to quantify P inputs, outputs, and retention in a forested- agricultural watershed. The P budget showed that chemical fertilizers and organic compost were the largest source of P (97.6% of the total) followed by atmospheric deposition (2.1% of the total P), whereas forest export (0.2% of the total) and sewage treatment plants (STPs) (0.1% of the total) were negligible. The dominant P outputs were crop harvesting and hydrologic export to surface water. The P balance showed a significant accumulation of P in the watershed; approximately 87% of the total P input was retained in the soils within the watershed. However, P concentrations in drainage water were still high enough to cause eutrophication of downstream reservoirs. The results provide useful information on the proportion of P export and retention in soils and will help support efforts to improve water quality and design better management of agricultural non-point source pollution.

Mostly populous city like Chennai is subjected to frequent flooding due to its complex nature of natural and man-made activities. From the analysis of the past records of flood events of 1943,1976,1985,2005 and 2008,it has been observed Adayar watershed is subjected to cataclysmic flooding in low-lying areas of the city and its suburbs because of inoperativeness of the local drainage system, rainfall associated with cyclonic activity, topography of the terrain, encroachments along the floodplain, hugh upstream flow discharge into the river and the highly impervious area which blocked the runoff to flow into the storm water drainage. After looking into these problems of flooding, a study have been conducted on Adayar watershed to develop a 2D hydrodynamic model for the two scenarios of existing condition of storm water drainage network and revised conditions of storm water drainage network using high resolution Lidar DEM to assess the volume of runoff with respect to time and duration on flood peaks for the two flood events of 2005 and 2015.Secondly to develop a 1D flood model to predict the river stages during peak floods using MIKE 11 for the Adayar watershed. Thirdly to integrate the coupled 1D and 2D model using MIKEFLOOD for assessing the extent of inundation in the floodplain area of Adayar river. Finally results from the integrated model have been validated and the results found satisfactory. As a part of mitigation measures, two flood mitigation measures have been adopted. One measure such as revised storm water drainage system which enhances the flood carrying capacity of the drains and results in less inundated area which solves the problem of urban flooding and second measure such as regrading the river bed which reduces the floodplain inundation around the adjacent area of the river. After adopting these measures, the river is free to flow into the sea without any blockades.

Microbial contamination is now more common than chemical contamination in Tibet, and water-borne microbes can cause a number of diseases that threaten public health. Thus, in order to clarify the spatiotemporal distribution of bacteria in small watersheds for which there is no data in Tibet, we set up four sampling points along an upstream-downstream transect of the Xincang River Basin. We collected 239 water samples in 2014 and 2015, and evaluated their total constituent numbers of bacteria (TB) and coliforms (TC). The results of this study show that the microbial contamination of the Xincang River Basin is mild-to-moderate in terms of TB and TC contents, and that these concentrations vary significantly in different seasons. Results show that in summer TB and TC concentrations in the downstream section of this river were highest and that microbial contamination was most serious. Data also demonstrate that precipitation is the most important factor underlying increases in TB and TC concentrations during the summer months; both these variables are significantly correlated with precipitation, while animal husbandry and domestic sewage are the main sources of microbial contamination overall. The results of this study are likely to reflect the basic characteristics of small watersheds for which there is no data to some extent, and are thus of significant practical importance for protecting their ecological environments and promoting sustainable development.

Localizing faults in a software is a tedious process. The manual approach is becoming impractical because of the large size and complexity of contemporary computer systems as well as their logs, which are often the primary source of information about the fault. Log-based Fault Localization (LBFL) is a popular method applied for this purpose. However, in real-world scenarios, this method is vulnerable to a large number of previously unseen log lines. In this paper, we propose a novel method that can guide programmers to the location of a fault by creating a hierarchy of log lines with the highest rank, selected by the traditional LBFL method. We use the intuition that the symptoms of faults are in the context of normal behavior, whereas suspicious log lines grouped together are from new or additional functionalities turned on during faulty execution. To obtain this context, we used unsupervised log sequence segmentation, which has been previously used to segment log sequences into meaningful segments. Experiments on real-life examples show that our method reduces the effort to find the most crucial logs by up to 64% compared to the traditional timestamp approach. We demonstrated that context is highly useful in advancing fault localization, showing the possibility of further speeding up the process.

While there are several ways to identify customer behaviors, few extract this value from information already in a database, much less extract relevant characteristics. This paper presents the development of a prototype using the recency, frequency, and monetary attributes for customer segmentation of a retail database. For this purpose, the standard K-means, K-medoids, and MiniBatch K-means were evaluated. The standard K-means clustering algorithm was more appropriate for data clustering than other algorithms as it remained stable until solutions with 6 clusters. The evaluation of the clusters’ quality was obtained through the internal validation indexes: Silhouette, Calinski Harabasz, and Davies Bouldin. Once consensus was not obtained, three external validation indexes were applied: global stability, stability per cluster, and segment-level stability across solutions. Six customer segments were obtained, identified by their unique behavior: Lost customers, disinterested customers, recent customers, less recent customers, loyal customers, and best customers. Their behavior was evidenced and analyzed, indicating trends and preferences.

Bone Scan Index (BSI) is an image biomarker for quantification on bone metastasis of cancers. To compute BSI, not only the hotspots (metastasis) but also the bones have to be segmented. Most related researches focus on binary classification on bone scintigraphy: having metastasis or none. Rare studies focus on pixelwise segmentation. In this study we compare three advanced convolutional neural network (CNN) based models to explore the bone segmentation on dataset in house. The best model is Mask R-CNN, which reaches the precision, sensitivity and F1-score: 0.93, 0.87, 0.90 for prostate cancer patients and 0.92, 0.86, 0.88 for breast cancer patients, respectively. The results are the average of 10-fold cross-validation, which reveals the reliability for clinical use on bone segmentation.

Since the emergence of convolutional neural networks (CNNs), and later vision transformers (ViTs), the standard paradigm for model development has been using a set of identical block types with varying parameters/hyper-parameters. To leverage the benefits of different architectural designs (e.g., CNNs and ViTs), we propose alternating structurally different types of blocks to generate a new architecture, mimicking how Lego blocks can be assembled. Using two CNN-based and one SwinViT-based blocks, we investigate three variations to the so-called LegoNet that apply the new block alternation concept for the segmentation task in medical imaging. We also study a new clinical problem that has not been investigated before – the right internal mammary artery (RIMA) and perivascular space segmentation from computed tomography angiography (CTA). It was proven to demonstrate a prognostic value to primary cardiovascular outcomes. We compare the model performance against popular CNN and ViT architectures using two large datasets (achieving 0.749 dice similarity coefficient (DSC) on the larger dataset). We also evaluate the model’s performance on three external testing cohorts, where an expert clinician corrected model-segmented results (DSC>0.90 for the three cohorts). To assess our proposed model for suitability in clinical use, we perform intra- and inter-observer variability analysis. Finally, we investigate a joint self-supervised learning approach to determine its impact on model performance.

As we all know, many more dynamic objects appear almost continuously in real world, which are immensely able to impair the performance of the majority of vision-based SLAM systems that are based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in the high dynamic environment, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken influences of dynamic content, the moving object detection method was put forward in our visual odometry, then the semantic segmentation network was combined into our stereo SLAM to extract pixel-level contours of dynamic objects. Then influences of dynamic objects were extremely weaken and the performance of our system was increased markedly in dynamic, complex and crowed city spaces. Experiment with both on KITTI Odometry dataset and in a real-life scene, the results show that our method can dramatically decrease the tracking error or drift, improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios.

Object segmentation is still considered a challenging problem in autonomous driving, particularly in consideration of real world conditions. Following this line of research, this paper approaches the problem of object segmentation using LiDAR-camera fusion and semi-supervised learning implemented in a fully-convolutional neural network. Our method is tested on real-world data acquired using our custom vehicle iseAuto shuttle. The data include all-weather scenarios, featuring night and rainy weather. In this work, it is shown that LiDAR-camera fusion with only a few annotated scenarios and semi-supervised learning, it is possible to achieve robust performance on real-world data in a multi-class object segmentation problem. The performance of our algorithm is measured in terms of intersection over union, precision, recall and area-under-the-curve average precision. Our network achieves 82% IoU in vehicle detection in day fair scenarios and 64% IoU in vehicle segmentation in night rain scenarios.

Worldwide, hundreds of thousands of people are diagnosed with kidney cancer and this disease is more common in developed and industrialized countries. Previously, kidney cancer was known as an elderly disease and was seen in people over a certain age; nowadays it is also seen in younger individuals and it is easier to diagnose thanks to new radiological diagnostic methods. A kidney tumor is a type of cancer that is extremely aggressive and needs surgical treatment rapidly. Today, approximately 30% of patients diagnosed with kidney cancer are unfortunately noticed at the stage of metastatic disease (spread to distant organs). The biggest factor that pushes us to this study is that kidney tumors progress unlike other cancer types with little or no symptoms. Therefore, conducting such studies is extremely important for early diagnosis. In this study, we compare the Unet3D models in order to help people who are dealing with difficulties in the diagnosis of kidney cancer. Unet, Unet+ResNet and Unet++ models were compared for image segmentation.

Clinically, knowing the number of red blood cells (RBCs) and white blood cells (WBCs) helps doctors to make the better decision on accurate diagnosis of numerous diseases. The manual cell counting is a very time-consuming and expensive process, and it depends on the experience of specialists. Therefore, a completely automatic method supporting cell counting is a viable solution for clinical laboratories. This paper proposes a novel blood cell counting procedure to address this challenge. The proposed method adopts SegNet - a deep learning semantic segmentation to simultaneously segment RBCs and WBCs. The global accuracy of the segmentation of WBCs, RBCs, and the background of peripheral blood smear images obtains 89% when segment WBCs and RBCs from the background of blood smear images. Moreover, an effective solution to separate grouped or overlapping cells and cell count is presented using Euclidean distance transform, local maxima, and connected component labeling. The counting result of the proposed procedure achieves an accuracy of 93.3% for red blood cell count using dataset 1 and 97.38% for white blood cell count using dataset 2.

The eutrophication caused by excessive total nitrogen(TN) and total phosphorus(TP) emissions has been widely concerned by the whole society. Studies have revealed the relationship between land use and TN and TP, but the relationship between land use compound topographic position and TP and TN was seldom studied. Therefore, Spearman correlation and redundancy analyses were used to reveal the relationship between land use compound topographic position and TN and TP based on the monthly data of 28 water quality sampling sites and the land use data of 2013 and 2016 in the lakes of Guizhou Plateau. The results show that the nutritional state of the HBA watershed is medium. The trophic level index (TLI) value and TN concentration were high during flood, while TP concentration was high in dry period. The TN concentration in the tributaries was higher than that in the reservoir area. Construction and valley were the sources of the pollution, whereas forest land and gentle slope were the sink. According to the”source-sink”effect, the optimal zoning of land use was completed, and the urban land pollution govern area should be strengthened firstly. This paper can provide decision support for water environment management and sustainable development decision-making.

Digital Elevation Models (DEMs) are essential in watershed delineation, but the sensitivity of simulated runoff to DEM resolution is poorly understood. This study investigates the impact of DEM resolution on topological attributes and simulated runoff in the Mahabad Dam watershed, Iran. To delineate the watershed, DEMs with 12.5 m, 30 m, and 90 m resolutions were acquired from the ALOS PALSAR, Space Shuttle Radar Topography Mission (SRTM), and ASTER global DEM data source, respectively. Watershed and streamlines were delineated in ArcGIS, with hydrologic analyses performed using the Soil and Water Assessment Tool (SWAT). Sensitivity analysis on parameters contributing to runoff was done using Sequential Uncertainties Fitting Ver-2 (SUFI-2) Algorithm, in SWAT Calibration and Uncertainty Procedures (SWAT-CUP) software. Results showed the watershed area, reach lengths, and elevations in the watershed varied due to DEM resolutions. Higher amounts of runoff were generated when DEMs with finer resolutions were implemented. The 12.5 m DEM generated 3.48% and 0.42% more runoff compared with 90 m and 30 m DEMs, respectively. SWAT-CUP results showed the sensitivity of parameters contributing to runoff changes under different DEM resolutions. Regardless of DEM resolution, surface properties, available water capacity, and moisture levels in the soil are the most sensitive parameters. As the distribution of slope changes in different DEM resolutions, surface parameters are most affected. The findings indicate to reduce computation time and speed up computation procedures, researchers may use DEMs with coarser resolutions at the expense of minor decreases in accuracy.

The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2)—a successor with enhanced architecture and a larger training corpus—we reassess these challenges. This paper introduces SAM2-Adapter, the first adapter designed to overcome the persistent limitations observed in SAM2 and achieve new state-of-the-art (SOTA) results in specific downstream tasks including medical image segmentation, camouflaged (concealed) object detection, and shadow detection. SAM2-Adapter builds on the SAM-Adapter's strengths, offering enhanced generalizability and composability for diverse applications. We present extensive experimental results demonstrating SAM2-Adapter's effectiveness. We show the potential and encourage the research community to leverage the SAM2 model with our SAM2-Adapter for achieving superior segmentation outcomes. Code, pre-trained models, and data processing protocols are available at http://tianrun-chen.github.io/SAM-Adaptor/.

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Machine learning-based image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and Severe weather conditions affects image quality, which affects the ac-curacy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U2-Net network was constructed using multi-scale inflation convolution and a multi-layer Convolutional Block Attention Module (CBAM) attention mechanism for the U2-Net network. The experiments showed that (1) data augmentation solved the problem of an insuffi-cient number of training samples to a certain extent and improved the accuracy of image seg-mentation. (2) This study designed a multilevel Gaussian noise data augmentation scheme to improve the network's ability to resist noise interference and achieve a more accurate segmenta-tion of images with different degrees of noise pollution. (3) The inclusion of a multi-scale inflation perceptron and multi-layer CBAM attention mechanism improved the ability of U2-Net network feature extraction and enhanced the model accuracy and generalization ability.

It is very difficult to accurately divide farmland and woodland in Gaofen 2 (GF-2) remote sensing image, because their single plant coverage is very small, and their spectra are very similar. The ratio of spatial resolution and one plant’s coverage area must be fully taken into account when designing the Convolutional Neural Network structure for extracting them from GF-2 image. We establish a Convolutional Encode Neural Networks model (CENN), The first layer has two sets of convolution kernels to learn the characteristics of farmland and woodland respectively, while the second layer is the encoder to encode the characteristics by transfer function, which can map the results to the corresponding category number. In the training stage, samples of farmland, woodland, and other categories are categorically used to train CENN, as soon as training is accomplished, CENN would acquire enough ability to accurately extract farmland and woodland from remote sensing images. The final extraction result is obtained by implementing per-pixel segmentation of images used to train the CENN. CENN is compared and analyzed with others such as Deep Belief Network (DBN), Full Convolutional Network (FCN), Deeplab Model. The results of experiments show that CENN can more accurately mine the characteristics of farmland and woodland, and it achieves its goal of extracting farmland and woodland with high precision from GF-2 images.

Multi-stakeholder participation processes in watershed management face challenges due to limited monitoring and baseline data, resulting in a lack of awareness among stakeholders about the current state of the watershed. This knowledge gap often leads to conflicts of interest, where the broader impacts of individual decisions are overlooked. To overcome these limitations, this paper explores the design and implementation of a Serious Game (SG) aimed at co-producing a watershed management plan at the basin scale within the specific context of the Campoalegre River basin in Colombia. By providing an interactive platform, the SG facilitates collaboration between local actors, who may be unfamiliar with existing watershed plans, and decision-makers. The goal is to create a participatory space where stakeholders can comprehend the watershed management plan structure and prioritize actions based on various climatic, social, and economic conditions. Following the application of the SGs, stakeholders demonstrated an improved understanding of the basin, fostering increased participation, open debate, and the proposal of actions. These outcomes serve as valuable inputs for the implementation of water management planning policies, showcasing the potential of SGs in bridging knowledge gaps, and fostering effective multi-stakeholder engagement.

Among other applications, radar-rainfall (RR) and QPE (Quantitative Precipitation Estimation) based on radar reflectivity, dual polarization variables, and multi-sensor information, provide important information for land surface hydrology, such as flood forecasting. Therefore, we developed a flood alert system using rainfall-runoff model forced with RR and QPE, and tipping-bucket observations to forecast river water levels (using rating-curves). In this study, we used an hourly dataset from an S-Band dual-polarimetric radar with two tropical R(Z) relations based distrometer data, a polarimetric R(Z,ZDR) algorithm from the literature and a multi-sensor approach using radar, satellite and rain gauge. Two hydrological models were used and calibrated using observed discharge time-series. Although our previous studies indicated accurate RR-based simulations, in some cases floods were not detected when using catchment-lumped rainfall derived from multi-sensor QPE. In this study, we advance further in this subject using improved R(Z,ZDR) relations and QPE for the period of 2016-2017 and flood event-based rainfall-runoff calibration. Thus, we focused on the development (and timing) of floods in the Marrecas River can be complex and strongly related to storms spatiotemporal distribution. To explore this aspect, we also perform a first analysis in using RR in rainfall-runoff model with a nested catchment discretization.