Remote Sensing Applications-Society and Environment最新文献

{"title":"Assessing development patterns and carrying capacity using nighttime light analysis: A case study in Greece","authors":"Michalis Koimtzidis ,&nbsp;George Falalakis ,&nbsp;Stavros Stathopoulos ,&nbsp;Odysseas Kopsidas ,&nbsp;Konstantinos Kourtidis ,&nbsp;Alexandra Gemitzi","doi":"10.1016/j.rsase.2025.101462","DOIUrl":"10.1016/j.rsase.2025.101462","url":null,"abstract":"<div><div>In this work we present an approach for analysis of remotely sensed nightlights in order to determine the intensity and the spatiotemporal variability of human activities. Thus, the temporal trend and the seasonal and spatial patterns of the 326 municipalities of Greece were analyzed in order to recognize areas of intensive human activities either associated with urban or industrial activities and infrastructures which have low seasonality, or with tourism which exhibits substantial seasonal patterns. Comparison of the results with the Carrying Capacity for Development Index (CCDI) for Greece, highlights areas where intense economic activities are concentrated in areas with limited resources. Results indicate that most of the Southern Aegean islands, certain municipalities in Northern Crete, Southern Peloponnese and Chalkidiki, all popular summer destinations, are facing serious threats to their social and environmental balance and consequently to the achievement of the Sustainable Development Goals (SDGs), from the intensification of human activities. Those areas should be the focus of the local development plans of the country, in order to avoid further adverse impacts on the local population and the environment.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101462"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143091977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic landslide prioritization at regional scale through PS-InSAR cluster analysis and socio-economic impacts","authors":"Marta Zocchi,&nbsp;Claudia Masciulli,&nbsp;Giandomenico Mastrantoni,&nbsp;Francesco Troiani,&nbsp;Paolo Mazzanti,&nbsp;Gabriele Scarascia Mugnozza","doi":"10.1016/j.rsase.2024.101414","DOIUrl":"10.1016/j.rsase.2024.101414","url":null,"abstract":"<div><div>The 2016-2017 seismic sequence in the Central Apennines (Italy) necessitated a comprehensive revision of the Hydrogeological Asset Plans landslide database to support post-seismic reconstruction. To address this critical need for updated risk assessment, this study aims to develop and validate an automated workflow for classifying and prioritizing landslide-prone areas, providing government institutions with a systematic approach to landslide risk assessment. Our innovative methodology integrates multi-sensor Persistent Scatterers (PS) interferometric data, advanced clustering techniques, and socio-economic factors to establish a standardized procedure for monitoring hazardous areas and optimizing resource allocation. The multi-sensor analysis reveals that approximately 6% of landslides are undetectable by interferometric technique, 45% show stability with no PS-detected deformation, and 19% are accurately mapped with deformation confined within their boundaries. Notably, 30% of analyzed landslides exhibit displacement beyond their mapped perimeters, indicating potential expansion or underestimation of their extent. This comprehensive classification enables authorities to identify and prioritize critical areas requiring immediate intervention based on hazard levels and socio-economic impact. The study concludes that this multi-sensor approach significantly enhances the efficiency of field inspections and territorial planning by providing a data-driven framework for intervention prioritization, ensuring that reconstruction efforts are both scientifically grounded and economically justified.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101414"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FusionFireNet: A CNN-LSTM model for short-term wildfire hotspot prediction utilizing spatio-temporal datasets","authors":"Niloofar Alizadeh ,&nbsp;Masoud Mahdianpari ,&nbsp;Emadoddin Hemmati ,&nbsp;Mohammad Marjani","doi":"10.1016/j.rsase.2024.101436","DOIUrl":"10.1016/j.rsase.2024.101436","url":null,"abstract":"<div><div>Recurrent wildfires pose an immense and urgent global challenge, as they endanger human lives and have significant consequences on society and the economy. In recent years, several studies proposed models aimed at predicting wildfire hotspots to mitigate these catastrophic events. However, the dynamic nature of environmental factors means that hotspot locations can change daily in British Columbia (BC), Canada. Therefore, this study introduces a deep-learning model for daily wildfire hotspot prediction called FusionFireNet. This model was trained using two primary data sources: remote sensing and environmental data. Environmental variables, including meteorological, topographical, and anthropogenic factors (such as distance, population density, and land cover), were collected across the study area with different temporal resolution. For instance, meteorological variables were collected with hourly temporal resolution over the 15 days preceding each wildfire event, along with cumulative maps, date, and coordination cells, while Moderate-Resolution Imaging Spectroradiometer (MODIS) satellite data from 15, 10, and 5 days prior were also utilized. To enhance the model's ability to capture temporal, spatial, and spatio-temporal features, an attention mechanism was incorporated to weigh each feature category. Performance evaluation employed multiple metrics, including Mean Squared Error (MSE), Intersection over Union (IoU), Area Under the Curve (AUC), and Dice Coefficient Loss (DCL). The model achieved notable results, with an AUC, IOU, MSE, and DCL of 98%, 0.46, 0.002, and 0.024, respectively. Furthermore, the study underscores the importance of spatio-temporal features in wildfire hotspot prediction. These findings can inform policy-making by identifying high-risk areas and guiding resource allocation. Policymakers can develop targeted prevention strategies, enabling stakeholders to implement proactive measures that enhance wildfire management and protect communities and natural resources.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101436"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating shoreline prediction accuracy with the Kalman filter model: A case study of Nijhum Dwip, Bay of Bengal","authors":"Anamika Das Kona ,&nbsp;Md Enamul Hoque ,&nbsp;Md Atiqur Rahman","doi":"10.1016/j.rsase.2025.101469","DOIUrl":"10.1016/j.rsase.2025.101469","url":null,"abstract":"<div><div>Shoreline dynamics play a critical role in coastal zone management and environmental conservation. This study investigates shoreline changes and predictions for Nijhum Dwip, located in the Meghna estuary, over the period from 1980 to 2020, with a forecast for 2030. Utilizing multi-temporal Landsat imagery, Digital Shoreline Analysis System (DSAS), and the Kalman Filter Model, the study analyzes spatial and temporal shoreline variations. Results indicate a significant accretion trend, particularly in Segment B, which exhibits a net shoreline movement of 1322.85 m and an average rate of 31.96 m/yr. Segment A shows moderate accretion, with an average rate of 7.79 m/yr. The Kalman Filter Model predicts a mean accretion of 1601.23 m by 2030, aligning with historical accretion patterns. Model validation through Root Mean Square Error (RMSE) analysis yields a value of 95 m, highlighting discrepancies between predicted and observed shoreline positions. This comprehensive study underscores the utility of advanced geospatial and statistical methods in coastal change monitoring and provides actionable insights for sustainable coastal management.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101469"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Remote sensing of vegetation trends: A review of methodological choices and sources of uncertainty","authors":"Hamid Darabi ,&nbsp;Ali Torabi Haghighi ,&nbsp;Björn Klöve ,&nbsp;Miska Luoto","doi":"10.1016/j.rsase.2025.101500","DOIUrl":"10.1016/j.rsase.2025.101500","url":null,"abstract":"<div><div>Long-term satellite data provide up-to-date measurements of terrestrial ecosystems. To accurately estimate vegetation trends, it is essential to carefully consider the methodological details within the satellite time series data. This review aims to i) identify the main methods for trend estimation by focusing on their requirements, and ii) highlight the potential sources of uncertainty in remote sensing of vegetation trends. Results showed that 92% of the studies used a linear model (linear regression, Man-Kendall test and Theil-Sen slope estimator). Non-linear patterns were considered in 8% of the studies by using Piecewise Linear Regression (PLR) and Breaks For Additive Seasonal and Trend (BFAST). Although linear methods have several important advantages, they require a thorough understanding of their limitations. Particularly, when data do not meet the assumption of linearity, they oversimplify complex patterns across sub-periods and cannot detect potential abrupt and unimodal changes. Results indicated that utilizing of different methods and sensors could validate the results. However, uncertainties stemming from methodological choices and cross-sensor comparisons complicate the interpretation of findings, adding to the complexity of the topic. We conclude that bias in sampling and irregularity of satellite observations over space and time are the main sources of uncertainty in vegetation trends, which has been addressed in the literature using maximum value composites. However, selecting maximum values for a specified time of a year loses other temporal information, and it can also be sensitive to outliers, leading to incorrect value composites and bias in results. We emphasize the need for a deep understanding of the complexities in time series data as a necessity for accurately estimating trends through detailed methodological choices.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101500"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved cloud screening of OceanSat-3 OCM-3 satellite imagery using machine learning algorithm","authors":"Chakradhar Rao Tandule,&nbsp;Mukunda M. Gogoi,&nbsp;S. Suresh Babu","doi":"10.1016/j.rsase.2025.101481","DOIUrl":"10.1016/j.rsase.2025.101481","url":null,"abstract":"<div><div>Cloud masking in satellite imagery is critical for quantitative remote sensing research and its practical applications. However, accurate cloud detection in satellite imagery acquired by the sensors with limited spectral bands remains a challenge. Here, we present a machine learning (ML) approach such as Support Vector Machine (SVM) and Random Forest (RF) for improved cloud screening of satellite imagery acquired by the Ocean Color Monitor-3 (OCM-3) onboard the OceanSat-3 (EOS-06). Adaptive threshold (AT) technique is also used to comprehend efficient cloud screening by ML algorithms. Spectral reflectance and cloud indices derived from OCM-3 measurements in the visible and near-infrared bands are used as ML features. Pixel-level comparisons with visually inspected reference cloud masks over distinct geographic regions of India and adjacent oceanic regions are conducted to evaluate the performance of both ML and AT algorithms. The results reveal that the ML algorithm outperforms the AT algorithm in most metrics for both thick and thin cloud detection. The ML algorithm demonstrates an accuracy of ∼94% for all types of clouds, compared to 84% for the AT algorithm. Overall, this study suggests that underlying surface-specific training samples are crucial for different cloud types to achieve improved cloud screening across diverse geographic regions.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101481"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143373055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Brighter Nights, safer cities? Exploring spatial link between VIIRS nightlight and urban crime risk","authors":"Subham Roy,&nbsp;Indrajit Roy Chowdhury","doi":"10.1016/j.rsase.2025.101489","DOIUrl":"10.1016/j.rsase.2025.101489","url":null,"abstract":"<div><div>Urban safety is critical for sustainable cities, especially in emerging countries such as India, where growing crime endangers community well-being and economic stability. This research examines the geographical association between nighttime light (NTL) intensity and urban property crime, namely theft and burglary in Siliguri City, India. This research seeks to answer the question: <em>Do well-illuminated areas experience lower property crime incidents compared to poorly-lit neighbourhoods?</em> The research uses NASA's Suomi NPP-VIIRS nightlight data from 2021 to 2023 to examine spatial patterns and relationships between NTL and urban crime, using spatial analytic methods. Furthermore, a Negative Binomial Regression Model (NBRM) confirms the hypothesis that areas with low NTL are more vulnerable to crime. The findings indicate a substantial negative association between NTL and urban crime, with brighter locations seeing lower crime rates. Northern neighbourhoods of the city with poor NTL had increased crime incidents, demonstrating vulnerability. Empirical evidence reveals that a one-unit increase in NTL intensity decreased larceny by 14.8% and burglary by 24.3%. Improved model performance, as shown in R², AIC, and BIC, emphasizes the significance of NTL in crime reduction. The results emphasize the need for strategic investments in lighting infrastructure as a key instrument for urban safety and policymaking.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101489"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MAPunet: High-resolution snow depth mapping through U-Net pixel-wise regression","authors":"Alejandro Betato ,&nbsp;Hernán Díaz Rodríguez ,&nbsp;Niamh French ,&nbsp;Thomas James ,&nbsp;Beatriz Remeseiro","doi":"10.1016/j.rsase.2025.101477","DOIUrl":"10.1016/j.rsase.2025.101477","url":null,"abstract":"<div><div>Accurate snow depth prediction is essential for hydrological risk assessment, flood prediction, water resource management, and weather forecasting. While previous studies have successfully applied deep learning techniques to generate snow depth maps, many have been constrained by geographical coverage or low data resolution. This work addresses these limitations by integrating high-resolution LiDAR maps, satellite imagery, digital elevation models, and three novel time-dependent variables. Additionally, the well-known U-Net architecture has been customized to perform pixel-wise regression and accurately predict snow depth over large geographic areas. The proposed method, called MAPunet, effectively models snow depth in the mountainous region of Davos, achieving an average error of 0.62 m at a 5 m resolution. The experimental results demonstrate the potential of combining high-resolution data with advanced deep learning techniques for enhanced snow depth mapping.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101477"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143346715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigation of atmospheric clouds and boundary layer dynamics during a dust storm in the Western-Indian region","authors":"Dharmendra Kumar Kamat ,&nbsp;Som Kumar Sharma ,&nbsp;Prashant Kumar ,&nbsp;Kondapalli Niranjan Kumar ,&nbsp;Aniket ,&nbsp;Sourita Saha ,&nbsp;Hassan Bencherif","doi":"10.1016/j.rsase.2024.101442","DOIUrl":"10.1016/j.rsase.2024.101442","url":null,"abstract":"<div><div>This study investigates the dynamics of atmospheric clouds and boundary layer due to a sudden dust storm over Ahmedabad (23.02° N, 72.57° E), a Western-Indian region, during the pre-monsoon season on May 13, 2024. The storm was triggered by the outflow from convective systems originating in southwest Gujarat and southeast Rajasthan, combined with the significant deepening of the thermal low core over Ahmedabad, which generated strong near-surface winds and initiated the dust storm. These systems and the dust storm were captured by the INSAT-3D satellite and MODIS instrument on NASA's Aqua and Terra satellites. The ground-based Ceilometer Lidar backscatter profile showed an abrupt change in the mixed layer height (MLH) from ∼2.5 km to about 250 m during the storm due to attenuation of the signal by heavy dust load. The MLH, ∼2 km on 12 May (previous day), shallowed to ∼800 m on 14 May (post dust storm day), with increased backscatter indicating high dust concentration. Vertical visibility dropped to 340–660 m during the dust storm. During the storm, relative humidity near the surface increased from 29% to 48% due to moisture transport by frontal system along the density current pathway, while near-surface wind speeds peaked at around 6–10 m/s. After the storm, deep convective clouds formed with a vertical extent of ∼11 km, resulting in approximately 19 mm of rainfall with nearly 15 mm falling within just 1 h indicating the dust-cloud interaction. This study highlights the impact of moist convection and subsequent dust storm on clouds and boundary layer dynamics, emphasizing the importance of ground-based instruments, satellites, and reanalysis datasets in atmospheric monitoring. Understanding the causes, mechanisms, and consequences of dust storms is critical for mitigating their effects and adapting to the changing climate patterns that may influence their frequency and intensity.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101442"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143128310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hedgerow map of Bavaria, Germany, based on orthophotos and convolutional neural networks","authors":"Verena Huber-García ,&nbsp;Jennifer Kriese ,&nbsp;Sarah Asam ,&nbsp;Mariel Dirscherl ,&nbsp;Michael Stellmach ,&nbsp;Johanna Buchner ,&nbsp;Kristel Kerler ,&nbsp;Ursula Gessner","doi":"10.1016/j.rsase.2025.101451","DOIUrl":"10.1016/j.rsase.2025.101451","url":null,"abstract":"<div><div>Hedgerows play a significant role in biodiversity preservation, carbon sequestration, soil stability and the ecological integrity of rural landscapes. Understanding their current condition and future development is therefore crucial for a range of stakeholders such as municipalities, state agencies or environmental organizations. The wall-to-wall mapping and characterization of hedgerows in-situ is, however, very labour-, time- and cost-intensive. This impedes a regular monitoring at adequate intervals. In the Federal State of Bavaria, Germany, the hedgerow biotope mapping is repeated every 20–30 years for each district. State-wide consistent and up-to-date data are hence not available. In this study we present an approach for mapping all hedgerows in Bavaria using orthophotos and deep learning. We used hedgerow polygons of the federal in-situ biotope mapping from 5 focus districts as well as additional manually digitized polygons as training and test data and orthophotos as input in a DeepLabV3 Convolutional Neural Network (CNN). The CNN has a Resnet50 Backbone and was optimized using the Dice loss as cost function. The orthophotos were acquired in 2019–2021. They have a spatial resolution of 20 cm and were fed to the CNN at tiles of 125 × 125 m. The generated hedgerow probability tiles were post-processed through merging and averaging the overlapping tile boarders, shape simplification and filtering. The resulting hedgerow vector data set achieved medium overall accuracies (precision = 0.43, recall = 0.53, F1-score = 0.48). The model generally overestimated the number of hedgerows, and hedgerows were often confused with riparian as well as urban vegetation. Looking at each hedgerow polygon individually, the mapping accuracy varied considerably, with a median F1-score of 0.51 for all detected objects. In addition, we found differences in accuracies among districts in different landscapes. For example, the Hassberge district, a landscape rich of hedgerows, reached a F1-score of 0.61. A comprehensive comparison with the Copernicus High Resolution Layer (HRL) Small Woody Features (SWF) revealed significant differences between the datasets. About 43 % of the hedgerows in our data set were not present in the SWF layer. Especially narrow, elongated vegetated structures are not captured in the SWF product. This highlights the potential to use our state-wide hedgerow map of Bavaria in combination with the SWF dataset, but also by itself, for a range of administrative, statistical and nature conservation applications.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101451"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143091975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}