Search Results (384)

Detecting clouds, snow, and lakes in remote sensing images is vital due to their propensity to obscure underlying surface information and hinder data extraction. In this study, we utilize Sentinel-2 images to implement a two-stage random forest (RF) algorithm for image labeling and delve into the factors influencing neural network performance across six aspects: model architecture, encoder, learning rate adjustment strategy, loss function, input image size, and different band combinations. Our findings indicate the Feature Pyramid Network (FPN) achieved the highest MIoU of 87.14%. The multi-head self-attention mechanism was less effective compared to convolutional methods for feature extraction with small datasets. Incorporating residual connections into convolutional blocks notably enhanced performance. Additionally, employing false-color images (bands 12-3-2) yielded a 4.86% improvement in MIoU compared to true-color images (bands 4-3-2). Notably, variations in model architecture, encoder structure, and input band combination had a substantial impact on performance, with parameter variations resulting in MIoU differences exceeding 5%. These results provide a reference for high-precision segmentation of clouds, snow, and lakes and offer valuable insights for applying deep learning techniques to the high-precision extraction of information from remote sensing images, thereby advancing research in deep neural networks for semantic segmentation. Full article

Sea ice is a crucial component of the global climate system. The China–French Ocean Satellite Scatterometer (CFOSAT/SCAT, CSCAT) employs an innovative rotating fan beam system. This study applied principal component analysis (PCA) to extract classification features and developed an ensemble machine learning approach for sea ice detection. PCA identified key features from CSCAT’s backscatter information, representing outer and sweet swath observations. The ensemble model’s performances (OA and Kappa) for the Northern and Southern Hemispheres were 0.930, 0.899, and 0.844, 0.747, respectively. CSCAT achieved an accuracy of over 0.9 for close ice and open water but less than 0.3 for open ice, with misclassification of open ice as closed ice. The sea ice extent discrepancy between CSCAT and the National Snow and Ice Data Center (NSIDC) was −0.06 ± 0.36 million km² in the Northern Hemisphere and −0.03 ± 0.48 million km² in the Southern Hemisphere. CSCAT’s sea ice closely matched synthetic aperture radar (SAR) imagery, indicating effective sea ice and open water differentiation. CSCAT accurately distinguished sea ice from open water but struggled with open ice classification, with misclassifications in the Arctic’s Greenland Sea and Hudson Bay, and the Antarctic’s sea ice–water boundary. Full article

Different blood group systems have been characterized in people and other mammals. In domestic cats, the ABC blood group system plays the most important clinical role and has been investigated extensively—from the phenotype to the molecular genetics. In non-domestic felids, phenotypic ABC blood typing has been performed by different methods to detect the antigens, but the four informative CMAH markers in domestic cats were not able to identify types B and C (AB) in non-domestic cats. In this study, 138 blood samples from 15 non-domestic (wild) felid species were investigated by CMAH exonic sequencing and genotyping for putative variants causing type B or C (AB) and correlation to the respective ABC blood phenotype. A total of 58 CMAH variants were found, including 15 missense and 43 synonymous CMAH variants. One variant (c.635G>C) was concordant with blood type B (and C) in cheetahs and type B in cougars, compared to blood type A in all other felid species (lion, tiger, Canada lynx, snow leopard, clouded leopard, serval, jaguar, fishing cat, Pallas cat, bobcat, black footed cat, leopard, and sand cat). Since cheetahs and cougars belong to the genera puma, it could not be determined if the common CMAH variant is either a marker for type B (or C) or is just common in pumas. Full article

Understanding the dietary preferences and ecological niche characteristics of mammals not only reveals their adaptive strategies under environmental changes but also reveals the interspecific relationships and coexistence mechanisms among sympatric species. Nevertheless, such data are scarce for rodents inhabiting areas spanning a wide altitude range. This study employed DNA metabarcoding technology to analyze the stomach contents of Apodemus ilex, Apodemus chevrieri, and Niviventer confucianus, aiming to investigate their dietary compositions and diversity in the Meili Snow Mountain in Yunnan Province, China. Levins’s and Pianka’s indices were used to compare the interspecific niche breadth and niche overlaps. The results revealed the following: (1) Insecta (relative abundance: 59.4–78.4%) and Clitellata (relative abundance: 5.2–25.5%) were the primary animal food sources for the three species, while Magnoliopsida (relative abundance: 90.3–99.9%) constitutes their main plant food source. Considerable interspecific differences were detected in the relative abundance of primary animal and plant foods among the three species; (2) There was partial overlap in the genus-level animal food between A. ilex and N. confucianus (O_jk = 0.4648), and partial overlap in plant food between A. ilex and A. chevrieri (O_jk = 0.3418). However, no overlap exists between A. chevrieri and N. confucianus, either in animal or plant food; (3) There were no significant interspecific differences in the α-diversity of animal and plant foods among the three species. The feeding strategies and ecological niche variations of these rodents support the niche differentiation hypothesis, indicating that they have diversified in their primary food sources. This diversification may be a strategy to reduce competition and achieve long-term coexistence by adjusting the types and proportions of primary foods consumed. Full article

Understanding subnivean life is crucial, particularly due to the major role in food webs played by small animals inhabiting this poorly known habitat. However, challenges such as remoteness and prolonged, harsh winters in the Arctic have hampered our understanding of subnivean ecology in this region. To address this problem, we present an improved autonomous, low-power system for monitoring small mammals under the snow in the Arctic. It comprises a compact camera paired with a single-board computer for video acquisition, a low-power-microcontroller-based circuit to regulate video acquisition timing, and motion detection circuits. We also introduce a novel low-power method of gathering complementary information on animal activities using passive infrared sensors. Meticulously designed to withstand extreme cold, prolonged operation periods, and the limited energy provided by batteries, the system’s efficacy is demonstrated through laboratory tests and field trials in the Canadian Arctic. Notably, our system achieves a standby power consumption of approximately 60 µW, representing a seventy-fold reduction compared to previous equipment. The system recorded unique videos of animal life under the snow in the High Arctic. This system equips ecologists with enhanced capabilities to study subnivean life in the Arctic, potentially providing insights to address longstanding questions in ecology. Full article

This paper introduces an anchorless deep learning model designed for efficient analysis and processing of large-scale 3D synthetic traffic sign board datasets. With an ever-increasing emphasis on autonomous driving systems and their reliance on precise environmental perception, the ability to accurately interpret traffic sign information is crucial. Our model seamlessly integrates object detection, depth estimation, deformable parts, and text character extraction functionalities, facilitating a comprehensive understanding of road signs in simulated environments that mimic the real world. The dataset used has a large number of artificially generated traffic signs for 183 different classes. The signs include place names in Japanese and English, expressway names in Japanese and English, distances and motorway numbers, and direction arrow marks with different lighting, occlusion, viewing angles, camera distortion, day and night cycles, and bad weather like rain, snow, and fog. This was done so that the model could be tested thoroughly in a wide range of difficult conditions. We developed a convolutional neural network with a modified lightweight hourglass backbone using depthwise spatial and pointwise convolutions, along with spatial and channel attention modules that produce resilient feature maps. We conducted experiments to benchmark our model against the baseline model, showing improved accuracy and efficiency in both depth estimation and text extraction tasks, crucial for real-time applications in autonomous navigation systems. With its model efficiency and partwise decoded predictions, along with Optical Character Recognition (OCR), our approach suggests its potential as a valuable tool for developers of Advanced Driver-Assistance Systems (ADAS), Autonomous Vehicle (AV) technologies, and transportation safety applications, ensuring reliable navigation solutions. Full article

Sentinel-2 satellites are one of the major instruments in remote sensing (RS) technology that has revolutionized Earth observation research, as its main goal is to offer high-resolution satellite data for dynamic monitoring of Earth’s surface and climate change detection amongst others. However, visual observation of Sentinel-2 satellite data has revealed that most images obtained during the winter season contain snow noise, posing a major challenge and impediment to satellite RS analysis of land surface. This singular effect hampers satellite signals from capturing important surface features within the geographical area of interest. Consequently, it leads to information loss, image processing problems due to contamination, and masking effects, all of which can reduce the accuracy of image analysis. In this study, we developed a snow-cover removal (SCR) model based on the Cycle-Consistent Adversarial Networks (CycleGANs) architecture. Data augmentation procedures were carried out to salvage the effect of the limited availability of Sentinel-2 image data. Sentinel-2 satellite images were used for model training and the development of a novel SCR model. The SCR model captures snow and other prominent features in the Sentinel-2 satellite image and then generates a new snow-free synthetic optical image that shares the same characteristics as the source satellite image. The snow-free synthetic images generated are evaluated to quantify their visual and semantic similarity with original snow-free Sentinel-2 satellite images by using different image qualitative metrics (IQMs) such as Structural Similarity Index Measure (SSIM), Universal image quality index (Q), and peak signal-to-noise ratio (PSNR). The estimated metric data shows that Q delivers more metric values, nearly 95%, than SSIM and PRSN. The methodology presented in this study could be beneficial for RS research in DL model development for environmental mapping and time series modeling. The results also confirm the DL technique’s applicability in RS studies. Full article

Although existing 3D object-detection methods have achieved promising results on conventional datasets, it is still challenging to detect objects in data collected under adverse weather conditions. Data distortion from LiDAR and cameras in such conditions leads to poor performance of traditional single-sensor detection methods. Multi-modal data-fusion methods struggle with data distortion and low alignment accuracy, making accurate target detection difficult. To address this, we propose a multi-modal object-detection algorithm, Snow-CLOCs, specifically for snowy conditions. In image detection, we improved the YOLOv5 algorithm by integrating the InceptionNeXt network to enhance feature extraction and using the Wise-IoU algorithm to reduce dependency on high-quality data. For LiDAR point-cloud detection, we built upon the SECOND algorithm and employed the DROR filter to remove noise, enhancing detection accuracy. We combined the detection results from the camera and LiDAR into a unified detection set, represented using a sparse tensor, and extracted features through a 2D convolutional neural network to achieve object detection and localization. Snow-CLOCs achieved a detection accuracy of 86.61% for vehicle detection in snowy conditions. Full article

Snow cover and runoff play an important role in the Arctic environment, which is increasingly affected by climate change. Over the past 30 years, winter temperatures in northern Sweden have risen by 2 °C, accompanied by an increase in precipitation. This has led to a higher incidence of thaw–freeze and rain-on-snow events. Snow properties, such as the snow depth and longevity, and the timing of snowmelt in spring significantly impact the alpine tundra vegetation. The emergent vegetation at the edge of the snow patches during spring and summer constitutes an essential nutrient supply for reindeer. We have used Sentinel-1 synthetic aperture radar (SAR) to determine the onset of the surface melt and the end of the snow cover in the core reindeer grazing area of the Laevás Sámi reindeer-herding community in northern Sweden. Using SAR data from March to August during the period 2017 to 2021, the start of the surface melt is identified by detecting the season’s backscatter minimum. The end of the snow cover is determined using a threshold approach. A comparison between the results of the analysis of the end of the snow cover from Sentinel-1 and in situ measurements, for the years 2017 to 2020, derived from an automatic weather station located in Laevásvággi reveals a 2- to 10-day difference in the snow-free ground conditions, which indicates that the method can be used to investigate when the ground is free of snow. VH data are preferred to VV data due to the former’s lower sensitivity to temporary wetting events. The outcomes from the season backscatter minimum demonstrate a distinct 25-day difference in the start of the runoff between the 5 investigated years. The backscatter minimum and threshold-based method used here serves as a valuable complement to global snowmelt monitoring. Full article

Snow cover products are primarily derived from the Moderate-resolution Imaging Spectrometer (MODIS) and Advanced Very-High-Resolution Radiometer (AVHRR) datasets. MODIS achieves both snow/non-snow discrimination and snow cover fractional retrieval, while early AVHRR-based snow cover products only focused on snow/non-snow discrimination. The AVHRR Climate Data Record (AVHRR-CDR) provides a nearly 40-year global dataset that has the potential to fill the gap in long-term snow cover fractional monitoring. Our study selects the Qinghai–Tibet Plateau as the experimental area, utilizing AVHRR-CDR surface reflectance data (AVH09C1) and calibrating with the MODIS snow product MOD10A1. The snow cover percentage retrieval from the AVHRR dataset is performed using Surface Reflectance at 0.64 μm (SR1) and Surface Reflectance at 0.86 μm (SR2), along with a simulated Normalized Difference Snow Index (NDSI) model. Also, in order to detect the effects of land-cover type and topography on snow inversion, we tested the accuracy of the algorithm with and without these influences, respectively (vanilla algorithm and improved algorithm). The accuracy of the AVHRR snow cover percentage data product is evaluated using MOD10A1, ground snow-depth measurements and ERA5. The results indicate that the logic model based on NDSI has the best fitting effect, with R-square and RMSE values of 0.83 and 0.10, respectively. Meanwhile, the accuracy was improved after taking into account the effects of land-cover type and topography. The model is validated using MOD10A1 snow-covered areas, showing snow cover area differences of less than 4% across 6 temporal phases. The improved algorithm results in better consistency with MOD10A1 than with the vanilla algorithm. Moreover, the RMSE reaches greater levels when the elevation is below 2000 m or above 6000 m and is lower when the slope is between 16° and 20°. Using ground snow-depth measurements as ground truth, the multi-year recall rates are mostly above 0.7, with an average recall rate of 0.81. The results also show a high degree of consistency with ERA5. The validation results demonstrate that the AVHRR snow cover percentage remote sensing product proposed in this study exhibits high accuracy in the Tibetan Plateau region, also demonstrating that land-cover type and topographic factors are important to the algorithm. Our study lays the foundation for a global snow cover percentage product based on AVHRR-CDR and furthermore lays a basic work for generating a long-term AVHRR-MODIS fractional snow cover dataset. Full article

The impact of climates on the radial growth of muti-species remains insufficiently understood in the climate-sensitive southeastern Tibetan Plateau, and this hampers an effective assessment of forest growth under the background of global warming. Here, we studied the growth–climate relationships of three major species (Abies georgei, Larix potaninii, and Picea likiangensis) on the Baima Snow Mountain (BSM) by using dendrochronology methods. We constructed basal area increment (BAI) residual chronologies based on the dated ring-width measurements and correlated the chronologies with four climate factors. We also calculated the contributions of each climate factor to species growth. We found that photothermal conditions played a more important role than moisture in modulating radial growth, and P. likiangensi presented the strongest sensitivity to climate change among the three species. The growing season (June and July) temperature positively affected the radial growth of three species. Winter (previous December and current January) SD negatively impacted the tree growth of A. georgei and P. likiangensis. Significant correlations between growth and precipitation were detected only in A. georgei (January and May). Warming since the beginning of the 1950s promoted the growth of A. georgei and P. likiangensis, while the same effect on L. potaninii growth was found in the recent 50 years. Full article

Pepper is a high-economic-value agricultural crop that faces diverse disease challenges such as blight and anthracnose. These diseases not only reduce the yield of pepper but, in severe cases, can also cause significant economic losses and threaten food security. The timely and accurate identification of pepper diseases is crucial. Image recognition technology plays a key role in this aspect by automating and efficiently identifying pepper diseases, helping agricultural workers to adopt and implement effective control strategies, alleviating the impact of diseases, and being of great importance for improving agricultural production efficiency and promoting sustainable agricultural development. In response to issues such as edge-blurring and the extraction of minute features in pepper disease image recognition, as well as the difficulty in determining the optimal learning rate during the training process of traditional pepper disease identification networks, a new pepper disease recognition model based on the TPSAO-AMWNet is proposed. First, an Adaptive Residual Pyramid Convolution (ARPC) structure combined with a Squeeze-and-Excitation (SE) module is proposed to solve the problem of edge-blurring by utilizing adaptivity and channel attention; secondly, to address the issue of micro-feature extraction, Minor Triplet Disease Focus Attention (MTDFA) is proposed to enhance the capture of local details of pepper leaf disease features while maintaining attention to global features, reducing interference from irrelevant regions; then, a mixed loss function combining Weighted Focal Loss and L2 regularization (WfrLoss) is introduced to refine the learning strategy during dataset processing, enhancing the model’s performance and generalization capabilities while preventing overfitting. Subsequently, to tackle the challenge of determining the optimal learning rate, the tent particle snow ablation optimizer (TPSAO) is developed to accurately identify the most effective learning rate. The TPSAO-AMWNet model, trained on our custom datasets, is evaluated against other existing methods. The model attains an average accuracy of 93.52% and an F1 score of 93.15%, demonstrating robust effectiveness and practicality in classifying pepper diseases. These results also offer valuable insights for disease detection in various other crops. Full article

Compared to the southern Tibetan Plateau, the northern part has been regarded as relatively lacking geothermal resources. However, there is no lack of natural hot springs exposed in beads along large-scale fracture systems, and research on them is currently limited to individual hot springs or geothermal systems. This paper focuses on the Wahongshan-Wenquan Fracture Zone (WWFZ), analyzes the formation of five hydrothermal activity zones along the fracture zone in terms of differences in hot water hydrochemical and isotopic composition, and then explores the hot springs’ hydrothermal control in the fracture zone. The results show that the main fractures of the WWFZ are the regional heat control structures, and its near-north–south- and near-east–west-oriented fractures form a fracture system that provides favorable channels for deep hydrothermal convection. Ice and snow meltwater from the Elashan Mountains, with an average elevation of more than 4,500 m above sea level, infiltrates along the fractures, and is heated by deep circulation to form deep geothermal reservoirs. There is no detectable mantle contribution source heat to the hot spring gases, and the heat source is mainly natural heat conduction warming, but the “low-velocity body (LVB)” in the middle and lower crust may be the primary heat source of the high geothermal background in the area. The hot springs’ hydrochemical components show a certain regularity, and the main ionic components, TDS, and water temperature tend to increase away from the main rupture, reflecting the WWFZ controlling effect on hydrothermal transport. In the future, the geothermal research in this area should focus on the hydrothermal control properties of different levels, the nature of fractures, and the thermal contribution of the LVB in the middle and lower crust. Full article

The refractive index of a liquid serves as a fundamental parameter reflecting its composition, thereby enabling the determination of component concentrations in various fields such as chemical research, the food industry, and environmental monitoring. Traditional methods for refractive index (RI) measurement rely on light deflection angles at interfaces between the liquid and a material with a known refractive index. In this paper, the authors present a new differential refractometer for the highly sensitive measurement of RI differences between two liquid samples. Using a configuration with two cells equipped with flat parallel plates as measuring elements, the instrument facilitates accurate analysis. Namely, the sensor signals from both the solution and the solvent cuvette are generated simultaneously with one laser pulse, reducing the possible fluctuations in the laser radiation intensity. Our evaluation shows the high sensitivity of RI measurements $<{7\times 10}^{-6}$), so this differential refractometer can be proposed not only as a high-sensitivity sensing tool that can be used for mobile detection of nanoparticles in solution samples but also to determine the level of environmental nano-pollution using water (including rain, snow) samples from various natural as well as industrial sources, thus helping to solve some important environmental problems. Full article

Traffic sign recognition plays a crucial role in enhancing the safety and efficiency of traffic systems. However, in snowy conditions, traffic signs are often obscured by particles, leading to a severe decrease in detection accuracy. To address this challenge, we propose an improved YOLOv8-based model for traffic sign recognition. Initially, we introduce a Multi-Scale Group Convolution (MSGC) module to replace the C2f module in the YOLOv8 backbone. Data indicate that MSGC enhances detection accuracy while maintaining model lightweightness. Subsequently, to improve the recognition ability for small targets, we introduce an enhanced small target detection layer, which enhances small target detection accuracy while reducing parameters. In addition, we replaced the original BCE loss with the improved EfficientSlide loss to improve the sample imbalance problem. Finally, we integrate Deformable Attention into the model to improve the detection efficiency and performance of complex targets. The resulting fused model, named MSGC-YOLOv8, is evaluated on an enhanced dataset of snow-covered traffic signs. Experimental results show that the MSGC-YOLOv8 model is used for snow road traffic sign recognition. Compared with the YOLOv8n model [email protected]:0.95, [email protected]:0.95 is increased by 17.7% and 18.1%, respectively, greatly improving the detection accuracy. Compared with the YOLOv8s model, while the parameters are reduced by 59.6%, [email protected] only loses 1.5%. Considering all aspects of the data, our proposed model shows high detection efficiency and accuracy under snowy conditions. Full article