Search Results (94)

This paper addresses the classification of images depicting the eruptive activity of Mount Etna, captured by a network of ground-based thermal cameras. The proposed approach utilizes Convolutional Neural Networks (CNNs), focusing on pretrained models. Eight popular pretrained neural networks underwent systematic evaluation, revealing their effectiveness in addressing the classification problem. The experimental results demonstrated that, following a retraining phase with a limited dataset, specific networks such as VGG-16 and AlexNet, achieved an impressive total accuracy of approximately $90\%$. Notably, VGG-16 and AlexNet emerged as practical choices, exhibiting individual class accuracies exceeding $90\%$. The case study emphasized the pivotal role of transfer learning, as attempts to solve the classification problem without pretrained networks resulted in unsatisfactory outcomes. Full article

Effective management of water resources is crucial for sustainable development in any region. When considering computer-aided analysis for resource management, geospatial technology, i.e., the use of remote sensing (RS) combined with Geographic Information Systems (GIS) proves to be highly valuable. Geospatial technology is more cost-effective and requires less labor compared to ground-based surveys, making it highly suitable for a wide range of agricultural applications. Effectively utilizing the timely, accurate, and objective data provided by RS technologies presents a crucial challenge in the field of water resource management. Satellite-based RS measurements offer consistent information on agricultural and hydrological conditions across extensive land areas. In this study, we carried out a detailed analysis focused on addressing agricultural water management issues in India through the application of RS and GIS technologies. Adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines, we systematically reviewed published research articles, providing a comprehensive and detailed analysis. This study aims to explore the use of RS and GIS technologies in crucial agricultural water management practices with the goal of enhancing their effectiveness and efficiency. This study primarily examines the current use of geospatial technology in Indian agricultural water management and sustainability. We revealed that considerable research has primarily used multispectral Landsat series data. Cutting-edge technologies like Sentinel, Unmanned Aerial Vehicles (UAVs), and hyperspectral technology have not been fully investigated for the assessment and monitoring of water resources. Integrating RS and GIS allows for consistent agricultural monitoring, offering valuable recommendations for effective management. Full article

The ground reference dataset used in the assessment of classification accuracy is typically assumed implicitly to be perfect (i.e., 100% correct and representing ground truth). Rarely is this assumption valid, and errors in the ground dataset can cause the apparent accuracy of a classification to differ greatly from reality. The effect of variations in the quality in the ground dataset and of class abundance on accuracy assessment is explored. Using simulations of realistic scenarios encountered in remote sensing, it is shown that substantial bias can be introduced into a study through the use of an imperfect ground dataset. Specifically, estimates of accuracy on a per-class and overall basis, as well as of a derived variable, class areal extent, can be biased as a result of ground data error. The specific impacts of ground data error vary with the magnitude and nature of the errors, as well as the relative abundance of the classes. The community is urged to be wary of direct interpretation of accuracy assessments and to seek to address the problems that arise from the use of imperfect ground data. Full article

Many single-family homes built in Germany in the first decades following the Second World War are now occupied by elderly residents. If local conditions are unfavorable, a large number of these buildings may enter the real estate market in a short period of time and put pressure on the local housing market. Planners and decision-makers therefore need detailed spatiotemporal information about these neighborhoods to effectively address and counteract such developments. We present the design and implementation of a planning support system that can generate the required information. The architecture of this newly developed software consists of a composite, multitier framework to perform the complex tasks of data importation, data processing, and visualization. Legally mandated municipal population registers provide the key data for the calculation of indicators as a base for spatiotemporal analyses and visualizations. These registers offer high data quality in terms of completeness, logical consistency, spatial, and temporal and thematic accuracy. We demonstrate the implemented method using population data from a local government in a rural area in southwestern Germany. The results show that the new tool, which relies on open software components, is capable to identify and prioritize areas with particularly high levels of problem pressure. The tool can be used not only for analyses in a local context, but also at a regional level. Full article

The Italian territory of Sardinia Island has an enormous cultural and identity heritage from the Pre-Nuragic and Nuragic periods, with archaeological evidence of more than 7000 sites. However, many other undiscovered remnants of these ancient times are believed to be present. In this context, it can be helpful to analyze data from different types of sensors on a single information technology platform, to better identify and perimeter hidden archaeological structures. The main objective of the study is to define a methodology that through the processing, analysis, and comparison of data obtained using different non-invasive survey techniques could help to identify and document archaeological sites not yet or only partially investigated. The non-invasive techniques include satellite, unmanned aerial vehicle, and geophysical surveys that have been applied at the nuraghe Nanni Arrù, one of the most important finds in recent times. The complexity of this ancient megalithic edifice and its surroundings represents an ideal use case. The surveys showed some anomalies in the areas south–east and north–east of the excavated portion of the Nanni Arrù site. The comparison between data obtained with the different survey techniques used in the study suggests that in areas where anomalies have been confirmed by multiple data types, buried structures may be present. To confirm this hypothesis, further studies are believed necessary, for example, additional geophysical surveys in the excavated part of the site. Full article

A coordinated multi-year ocean exploration campaign on the Blake Plateau offshore of the southeastern U.S. has mapped what appears to be the most expansive cold-water coral (CWC) mound province thus far discovered. Nearly continuous CWC mound features span an area up to 500 km long and 110 km wide, with a core area of high-density mounds up to 254 km long by 42 km wide. This study synthesized bathymetric data from 31 multibeam sonar mapping surveys and generated a standardized geomorphic classification of the region in order to delineate and quantify CWC mound habitats and compare mound morphologies among subregions of the coral province. Based on the multibeam bathymetry, a total of 83,908 individual peak features were delineated, providing the first estimate of the overall number of potential CWC mounds mapped in the region to date. Five geomorphic landform classes were mapped and quantified: peaks (411 km²), valleys (3598 km²), ridges (3642 km²), slopes (23,082 km²), and flats (102,848 km²). The complex geomorphology of eight subregions was described qualitatively with geomorphic “fingerprints” (spatial patterns) and quantitatively by measurements of mound density and vertical relief. This study demonstrated the value of applying an objective automated terrain segmentation and classification approach to geomorphic characterization of a highly complex CWC mound province. Manual delineation of these features in a consistent repeatable way with a comparable level of detail would not have been possible. Full article

Physical and climatic variables such as Tree Canopy coverage, Normalized Difference Vegetation Index (NDVI), Distance to Roads, Distance to the Coast, Impervious Surface, and Precipitation can affect land surface temperature (LST). This paper examines the relationships using linear regression models and explores LST trends in the Miami Statistical Area (MSA) between 2002 and 2021. This study evaluates the effect of dry and wet seasons as well as day and night data on LST. A multiscale investigation is used to examine LST trends at the MSA scale, the individual county level, and at the pixel level to provide a detailed local perspective. The multiscale results are needed to understand spatiotemporal LST distributions to plan mitigation measures such as planting trees or greenery to regulate temperature and reduce the impacts of surface urban heat islands. The results indicate that LST values are rising in the MSA with a positive trend throughout the 20-year study period. The rate of change (RoC) for the wet season is smaller than for the dry season. The pixel-level analysis suggests that the RoC is primarily in rural areas and less apparent in urban areas. New development in rural areas may trigger increased RoC. This RoC relates to LST in the MSA and is different from global or regional RoC using air temperature. Results also suggest that climatic explanatory variables have different impacts during the night than they do in the daytime. For instance, the Tree Canopy variable has a positive coefficient, while during the day, the Tree Canopy variable has a negative relationship with LST. The Distance to the Coast variable changes from day to night as well. The increased granularity achieved with the multiscale analysis provides critical information needed to improve the effectiveness of potential mitigation efforts. Full article

Previous research showed that living closer to bus stops could be a factor in promoting a healthy and active lifestyle. However, most of the studies relied on self-reported measures of distance, which might be affected by several confounders. In this study, self-reported distances among study participants were compared to actual ones, computed by the use of GIS (Geographic Information System) technology and routing algorithms. We tested whether distance to the bus stop is associated with health and socioeconomic conditions of the respondents, using data among 2398 older people (75–90 years) in three cities in Sweden. We found that several variables including older age, female gender, living alone, and worse health status are associated with an over-estimation of bus stop distance. People who use public transport daily or several times a week and are satisfied with the walking environment in the neighbourhood tend to underestimate bus stop distances. Evidence based on self-reported measures only should be treated cautiously. Considering the limitations still present in open-data-based routing algorithms, the best indication is to combine the subjective with the objective measure of distance. Having the possibility to combine the two measures appears as a sound strategy to overcome the limitations associated with each single measure. Full article

Laser scanning technology has long been the preferred method for capturing interior scenes in various industries. With a growing market, smaller and more affordable scanners have emerged, offering end products with sufficient accuracy. While not on par with professional scanners, Apple has made laser scanning technology accessible to users with the introduction of the new iPhone Pro models, democratizing 3D scanning. Thus, this study aimed to assess the performance of the iPhone’s lidar technology as a low-cost solution for building documentation. Four scanning applications were evaluated to determine the accuracy, precision, and user experience of the generated point clouds compared with a terrestrial laser scanner. The results reveal varying performances on the same device, highlighting the influence of software. Notably, there is room for improvement, particularly in tracking the device’s position through software solutions. As it stands, the technology is well suited for applications such as indoor navigation and the generation of quick floor plans in the context of building documentation. Full article

OpenStreetMap (OSM) is among the most prominent Volunteered Geographic Information (VGI) initiatives, aiming to create a freely accessible world map. Despite its success, the data quality of OSM remains variable. This study begins by identifying the quality metrics proposed by earlier research to assess the quality of OSM building footprints. It then evaluates the quality of OSM building data from 2018 and 2023 for five cities within Québec, Canada. The analysis reveals a significant quality improvement over time. In 2018, the completeness of OSM building footprints in the examined cities averaged around 5%, while by 2023, it had increased to approximately 35%. However, this improvement was not evenly distributed. For example, Shawinigan saw its completeness surge from 2% to 99%. The study also finds that OSM contributors were more likely to digitize larger buildings before smaller ones. Positional accuracy saw enhancement, with the average error shrinking from 3.7 m in 2018 to 2.3 m in 2023. The average distance measure suggests a modest increase in shape accuracy over the same period. Overall, while the quality of OSM building footprints has indeed improved, this study shows that the extent of the improvement varied significantly across different cities. Shawinigan experienced a substantial increase in data quality compared to its counterparts. Full article

Sea-level rise (SLR) is a critical consequence of climate change, posing significant threats to coastal regions worldwide. Accurate and efficient assessment of potential inundation areas is crucial for effective coastal planning and adaptation strategies. This study aimed to explore the utility of free and open-source software for geospatial (FOSS4G) tools for mapping SLR inundation, providing cost-effective solutions that are accessible to researchers and policymakers. We employed a combination of geospatial data, including high-resolution elevation models, tidal data, and projected SLR scenarios. Utilizing widely available FOSS4G tools, like QGIS, GDAL/OGR, and GRASS GIS, we developed an integrated workflow to map inundation extents, using a passive bathtub approach for various SLR scenarios. We demonstrate the approach through a case study in Virginia Key, Florida, however, the methodology can be replicated in any area where the input datasets are available. This paper demonstrates that FOSS4G tools offer a reliable and accessible means to map SLR inundation, empowering stakeholders to assess coastal vulnerabilities and to devise sustainable adaptation measures. The open-source approach facilitates collaboration and reproducibility, fostering a comprehensive understanding of the potential impacts of SLR on coastal ecosystems and communities. Full article

Detecting changes in soil micro-relief in farmland helps to understand degradation processes like sheet erosion. Using the high-resolution technique of terrestrial laser scanning (TLS), we generated point clouds of three 2 × 3 m plots on a weekly basis from May to mid-June in 2022 on cultivated farmland in Germany. Three well-known applications for eliminating vegetation points in the generated point cloud were tested: Cloth Simulation Filter (CSF) as a filtering method, three variants of CANUPO as a machine learning method, and ArcGIS PointCNN as a deep learning method, a sub-category of machine learning using deep neural networks. We assessed the methods with hard criteria such as F1 score, balanced accuracy, height differences, and their standard deviations to the reference surface, resulting in data gaps and robustness, and with soft criteria such as time-saving capacity, accessibility, and user knowledge. All algorithms showed a low performance at the initial measurement epoch, increasing with later epochs. While most of the results demonstrate a better performance of ArcGIS PointCNN, this algorithm revealed an exceptionally low performance in plot 1, which is describable by the generalization gap. Although CANUPO variants created the highest amount of data gaps, we recommend that CANUPO include colour values in combination with CSF. Full article

Recently, the move from cost-tied to open-access data has led to the mushrooming of research in pursuit of algorithms for estimating the aboveground grass biomass (AGGB). Nevertheless, a comprehensive synthesis or direction on the milestones achieved or an overview of how these models perform is lacking. This study synthesises the research from decades of experiments in order to point researchers in the direction of what was achieved, the challenges faced, as well as how the models perform. A pool of findings from 108 remote sensing-based AGGB studies published from 1972 to 2020 show that about 19% of the remote sensing-based algorithms were tested in the savannah grasslands. An uneven annual publication yield was observed with approximately 36% of the research output from Asia, whereas countries in the global south yielded few publications (<10%). Optical sensors, particularly MODIS, remain a major source of satellite data for AGGB studies, whilst studies in the global south rarely use active sensors such as Sentinel-1. Optical data tend to produce low regression accuracies that are highly inconsistent across the studies compared to radar. The vegetation indices, particularly the Normalised Difference Vegetation Index (NDVI), remain as the most frequently used predictor variable. The predictor variables such as the sward height, red edge position and backscatter coefficients produced consistent accuracies. Deciding on the optimal algorithm for estimating the AGGB is daunting due to the lack of overlap in the grassland type, location, sensor types, and predictor variables, signalling the need for standardised remote sensing techniques, including data collection methods to ensure the transferability of remote sensing-based AGGB models across multiple locations. Full article

Open-source software applications, especially those useful for GIS, have been used in the field of geology both in research and teaching at the University of Urbino for decades. The experiences described in this article range from land-surveying cases to cartographic processing and 3D printing of geological models. History of their use and development is punctuated by trials, failures, and slowdowns, but the idea of using digital tools in areas where they are traditionally frowned upon, such as in soil geology, is now rooted in and validated by applications in projects of various types. Although the current situation is not definitive, given that the evolution of information technology provides increasingly faster tools that are performance-oriented and easier to use, this article aims to contribute to the development of methodologies through an exchange of information and experiences. Full article

This study delves into the patterns of urban expansion in Kabul, using Landsat and Sentinel satellite imagery as primary tools for analysis. We classified land use and land cover (LULC) into five distinct categories: water bodies, vegetation, barren land, barren rocky terrain, and buildings. The necessary data processing and analysis was conducted using ERDAS Imagine v.2015 and ArcGIS 10.8 software. Our main objective was to scrutinize changes in LULC across five discrete decades. Additionally, we traced the long-term evolution of built-up areas in Kabul from 1973 to 2020. The classified satellite images revealed significant changes across all categories. For instance, the area of built-up land reduced from 29.91% in 2013 to 23.84% in 2020, while barren land saw a decrease from 33.3% to 28.4% over the same period. Conversely, the proportion of barren rocky terrain exhibited an increase from 22.89% in 2013 to 29.97% in 2020. Minor yet notable shifts were observed in the categories of water bodies and vegetated land use. The percentage of water bodies shrank from 2.51% in 2003 to 1.30% in 2013, and the extent of vegetated land use showed a decline from 13.61% in 2003 to 12.6% in 2013. Our study unveiled evolving land use patterns over time, with specific periods recording an increase in barren land and a slight rise in vegetated areas. These findings underscored the dynamic transformation of Kabul’s urban landscape over the years, with significant implications for urban planning and sustainability. Full article