Remote Sensing Applications-Society and Environment最新文献

{"title":"Urban growth unveiled: Deep learning with satellite imagery for measuring 3D building-stock evolution in Urban China","authors":"Sebastiano Papini ,&nbsp;Susie Xi Rao ,&nbsp;Sapar Charyyev ,&nbsp;Muyang Jiang ,&nbsp;Peter H. Egger","doi":"10.1016/j.rsase.2025.101523","DOIUrl":"10.1016/j.rsase.2025.101523","url":null,"abstract":"<div><div>Time-series information on building stock is of paramount importance to study cities in a host of disciplines ranging from economics to urban planning. Such data are lacking in a consistently measured way and especially among dynamically growing cities in developing countries. Due to their rapid change, building stock data in these cities can offer insights into the determinants and consequences of urbanization. To be able to analyze urban structures effectively, the building stock needs to be measured with sufficient detail – at a resolution that makes individual buildings or small conglomerates thereof visible – and it needs to consider building height (or volume) with a satisfactory scope across cities to cover both large numbers and multi-year sequences of data. This study aims to develop a comprehensive pipeline for predicting building volume – including both footprint and height – across 1,537 urban areas in mainland China, covering more than 60% of the Chinese population over a seven-year period (2017–2023). With the advancement of deep learning in remote sensing, we can leverage state-of-the-art techniques to efficiently produce large-scale data for Chinese cities across years, which could be very time-consuming with traditional remote-sensing techniques. We compare the performance of several deep learning architectures for the task at hand. We demonstrate that the best performing approach leads to credible metrics of both footprint and height predictions and performs very competitively with respect to existing building-volume predictions. We also benchmark our results against other data sources such as real-estate listings and demonstrate the out-of-sample prediction capability of the proposed model.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101523"},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851605","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 the utility of multispectral remote sensing for monitoring forage crops: A case study of Sulla Coronaria in the Sicily region, Italy","authors":"Ramsha Khan ,&nbsp;Saurabh Shukla ,&nbsp;Filippo Fazzino ,&nbsp;Carmelo Federico D'Anna ,&nbsp;Erica Gagliano ,&nbsp;Michele Mangiameli ,&nbsp;Paolo Roccaro","doi":"10.1016/j.rsase.2025.101608","DOIUrl":"10.1016/j.rsase.2025.101608","url":null,"abstract":"<div><div>Traditional methods of agricultural monitoring are resource-intensive and becoming impractical, and agriculture benefits greatly from remote sensing technologies like satellite imagery. This offers efficient, scalable, and timely solutions for crop management and monitoring. With wide spatial coverage and high temporal resolution, satellite data enhances precision in land classification while reducing the need for extensive fieldwork. In this study monitoring of <em>Sulla Coronaria</em> (referred as Sulla hereafter) as an important Mediterranean forage crop was done using imagery from Sentinel-2 mission in the central Sicily region, Italy, of the Mediterranean basin. Three fields viz., Casale, Lipira, and Verbumcaudo were selected for the monitoring from November-2023 to May-2024. Based on the values of vegetation indices (VIs), all the three fields had similar results till the month of March-2024. However, from April-2024, both Lipira and Verbumcaudo had declining value of the VIs. The growth of Sulla plant was consistent for Casale field, and the best results were obtained in terms of all the VIs. Furthermore, aspect maps were also produced to understand a possible reason behind this. Dominance of east (67.5°–112.5°) and southeast (112.5°–157.5°) orientations in the Casale field suggest that it receives substantial morning sunlight, which can be beneficial for the early growth stages of Sulla. Whereas Verbumcaudo and Lipira fields receive more direct sunlight throughout the day and have more morning exposure that can influence crop growth and water requirements. The results from the study can be implemented to customize agricultural practices, selection of optimal fields, not just for Sulla cultivation but other crops as well, ensuring better yields and resource management.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101608"},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178505","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":"Monitoring chlorophyll a concentration in the Mar Menor coastal lagoon using ocean color sensors","authors":"Francisco Gómez-Jakobsen ,&nbsp;José G. Giménez ,&nbsp;José M. Cecilia ,&nbsp;Isabel Ferrera ,&nbsp;Lidia Yebra ,&nbsp;Eugenio Fraile-Nuez ,&nbsp;Marijn Oosterbaan ,&nbsp;Pedro Martínez-Martínez ,&nbsp;Víctor Orenes-Salazar ,&nbsp;Virginia Sandoval-Cánovas ,&nbsp;Antonio Ortolano-Muñoz ,&nbsp;Rocío García-Muñoz ,&nbsp;Patricia Pérez-Tórtola ,&nbsp;Juan M. Ruíz ,&nbsp;Jesús M. Mercado","doi":"10.1016/j.rsase.2025.101531","DOIUrl":"10.1016/j.rsase.2025.101531","url":null,"abstract":"<div><div>The Mar Menor coastal lagoon has experienced a severe eutrophication process since 2015, with its most visible effect being a series of phytoplankton blooms featured by unprecedentedly high and persistent concentrations of chlorophyll <em>a</em> in the water column. To better quantify and monitor these changes, two suitable chlorophyll concentration algorithms (referred to as BELA, short for BELich Algorithm) for the Mar Menor lagoon are proposed. These algorithms are derived from the analysis of thousands of reflectance spectra obtained from six satellite ocean color sensors, combined with <em>in situ</em> observations performed between 2016 and 2023. Our results demonstrate that the BELA algorithms can accurately estimate chlorophyll <em>a</em> concentration in the shallow waters of the Mar Menor lagoon for values above 2 mg m⁻³, a range consistent with various of the episodes of high productivity observed since 2015. These algorithms perform well for a variety of currently operational ocean color sensors and could be used in future planned missions. This versatility makes them a valuable tool for monitoring and assessing the environmental state of the lagoon.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101531"},"PeriodicalIF":3.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725667","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":"Advancements in crop mapping through remote sensing: A comprehensive review of concept, data sources, and procedures over four decades","authors":"Iman Khosravi","doi":"10.1016/j.rsase.2025.101527","DOIUrl":"10.1016/j.rsase.2025.101527","url":null,"abstract":"<div><div>Crop mapping, vital for informed decision-making in agricultural and food planning, relies on accurate and current information about the distribution of agronomic lands. Remote Sensing and Earth Observation technologies have emerged as indispensable tools, providing up-to-date data and images in diverse spatial and temporal resolutions, offering a practical and cost-effective alternative to traditional methods. This paper surveys over 400 publications spanning four decades, with a notable increase in studies after 2010, focusing on crop mapping and monitoring using remote sensing imagery. Categorizing these studies based on the type of remote sensing data utilized—optical, radar, or a combination thereof—it also delves into the diverse strategies employed, including attributes used, processing units, and classification algorithms. To date, there has not been a comprehensive review study specifically focused on crop mapping. This paper emphasizes the innovations and advancements in remote sensing technologies and their applications in crop mapping. It highlights the integration of cutting-edge deep learning techniques, the utilization of high-resolution satellite data, and the development of hybrid models that combine multiple data sources for enhanced accuracy. Furthermore, this review identifies emerging trends and future directions in the field, offering insights into the potential of new technologies and methodologies. Through this comprehensive overview of crop mapping studies published in reputable scientific journals between 1980 and 2024, we illuminate the dynamic landscape of this field and underscore the unique contributions of our review to the existing body of literature.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101527"},"PeriodicalIF":3.8,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725668","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 for environmentally responsive urban built environment: A review of tools, methods and gaps","authors":"Naga Venkata Sai Kumar Manapragada ,&nbsp;Moshe Mandelmilch ,&nbsp;Elena Roitberg ,&nbsp;Fadi Kizel ,&nbsp;Jonathan Natanian","doi":"10.1016/j.rsase.2025.101529","DOIUrl":"10.1016/j.rsase.2025.101529","url":null,"abstract":"<div><div>Urban-scale environmental performance evaluations are essential for designing cities that effectively respond to climate change and rapid urbanization. Remote Sensing (RS) technologies provide high-resolution, multi-scale, and temporal assessments across multiple interlinked environmental criteria. Despite its growing adoption in urban sustainability, a comprehensive review of RS's role in multi-criteria decision-making is still lacking. This review analyzes 124 research articles to explore RS applications in spatio-temporal analysis, impact evaluation, mitigation strategy assessment, and predictive modeling across five interconnected environmental criteria: urban air quality, urban heat, outdoor thermal comfort, building energy consumption, and solar potential. RS facilitates the integration of morphological, thermal, and meteorological data, enabling the evaluation of urban interdependence, such as the influence of urban form on air pollution dispersion, heat retention, and energy demand. Machine learning and AI-enhanced models improve air quality predictions, urban heat mitigation strategies, energy forecasting, and solar potential assessments. UAVs, LiDAR, and nanosatellite technologies further enhance real-time urban climate monitoring at finer spatial scales, supporting dynamic planning interventions. Despite challenges in data resolution, temporal coverage, and real-time monitoring, advancements in AI-driven downscaling, digital twins, and nano satellite networks continue to expand RS capabilities. By facilitating multi-criteria decision-making, RS empowers urban designers and policymakers to develop climate-adaptive, energy-efficient, and resilient cities, offering actionable insights for sustainable design and planning.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101529"},"PeriodicalIF":3.8,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697463","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":"Determination of evapotranspiration for citrus using SAFER algorithm in the Oriental Amazon","authors":"Francisco de Assis do Nascimento Leão ,&nbsp;Erivelto Mercante ,&nbsp;Wendel Kaian Mendonça Oliveira ,&nbsp;Marcio Antonio Vilas Boas ,&nbsp;Marcus Metri Correa ,&nbsp;Claudio Leones Bazzi ,&nbsp;Alberto Cruz da Silva Jr.","doi":"10.1016/j.rsase.2025.101526","DOIUrl":"10.1016/j.rsase.2025.101526","url":null,"abstract":"<div><div>A pivotal facet of irrigation management revolves around estimating evapotranspiration (ET). In this regard, the SAFER algorithm, applied to satellite imagery, emerges as a potential tool. This study aimed to quantify ET for orange and lime crops in the Amazon Region using the SAFER algorithm. Data comprised Landsat 7 and 8 satellite images coupled with meteorological station data from July to December 2021. The SAFER algorithm determines ET based on several metrics derived from satellite imagery, such as reflectance, surface albedo, Normalized Difference Vegetation Index (NDVI), spectral radiance, and surface temperature. It also uses reference evapotranspiration (ET₀) from the meteorological station, which is multiplied by the quotient of ET and ET₀ to obtain ET_SAFER. Then, the algorithm was validated based on the Penman-Monteith method, calculating mean absolute and relative errors. Average ET_SAFER values for lime and orange were 3.25 (±0.05) and 3.36 (±0.01), respectively. A maximum albedo of 0.40 was observed among crops in December, and a higher density of lime crops due to larger canopy volumes increased NDVI values. Landsat 7 and 8 satellite images can be used to calculate ET using the SAFER algorithm, as they offered valuable information that helped the algorithm estimate it accurately for the studied period. The ET_SAFER values obtained by the algorithm were consistent with the observed data (ET_C) and had an accuracy of 75 %. However, estimation accuracy was higher for lime trees (74 %) than for orange crops (60 %).</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101526"},"PeriodicalIF":3.8,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143686660","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":"Quantification and attribution of spectral variation in irrigated perennial tree crops","authors":"James Malcher ,&nbsp;David Robertson ,&nbsp;Galen Holt ,&nbsp;Rebecca E. Lester","doi":"10.1016/j.rsase.2025.101524","DOIUrl":"10.1016/j.rsase.2025.101524","url":null,"abstract":"<div><div>Satellite reflectance data are used for crop classification models globally, yet research on their robustness under varying temporal and spatial conditions is limited. We examined the effects of space, time, water availability and ontogeny on crop spectral distributions cross a large, heterogenous landscape, Australia's Murray-Darling Basin. We aimed for broad generality of our findings, and so used a large ground-truthed dataset from 2015, 2018, and 2021, covering multiple catchments and 12 crops. We characterised spectral distributions for each crop in each year and catchment before testing for differences due to space and time, and associated with the amount of water available from irrigation and rainfall. We also tested bareness metrics (as a surrogate for perennial crop ages) in almond plantations. We found that crop type explained the most variation, confirming the utility of satellite imagery for crop classification. Catchment and year both explained small but significant variation, emphasising the need for data collected over a range of spatial and temporal contexts. Water availability explained a significant but small proportion of variation in the data set (&lt;1 %), suggesting that crops were receiving sufficient water across the observed range or that spectral signatures did not vary much as a result. The effect of bareness metrics suggested possible significant variation caused by ontogeny. This study affirms the validity of spectral imagery for crop classification studies, whilst underscoring the importance of spatial, hydrologic and ontogenetic context. Future studies in crop classification should consider these factors to enhance the robustness of their models.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101524"},"PeriodicalIF":3.8,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143686659","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":"Assessing feature extraction, selection, and classification combinations for crop mapping using Sentinel-2 time series: A case study in northern Italy","authors":"Rahat Tufail,&nbsp;Patrizia Tassinari,&nbsp;Daniele Torreggiani","doi":"10.1016/j.rsase.2025.101525","DOIUrl":"10.1016/j.rsase.2025.101525","url":null,"abstract":"<div><div>Rural areas need constant monitoring to ensure sustainable farming and respond to environmental and climatic impacts. Over the last few decades, remote sensing data have been extensively used in agricultural monitoring, allowing cost-effective and efficient crop management. Selecting the suitable data combinations for crop mapping while reducing dimensionality and redundancy to speed up processing remains a challenge. This study address the challenges by testing and assessing the efficiency of various combinations of feature extraction, feature selection, and feature classification methods. We used Sentinel-2 time series data, which focused on spectral features and derived vegetation indices. Particularly, the red-edge indices which are critical for crop discrimination. To select the optimal data for classifiers, we have tested two feature selection techniques: Random Forest and Principal Component Analysis, for both spectral bands and vegetational indices. Then, we have employed three machine learning algorithms: Extreme Gradient Boost (XGB), Random Forest (RF), and Support Vector Machine (SVM) along with one deep learning approach, Pixel-Set Encoders and Temporal Self-Attention (PSETAE), to evaluate the datasets. The results suggest that the most effective feature set is the Sentinel-2 spectral bands selected by the Random Forest feature selection method. The results obtained from the previous step achieve the highest overall accuracy with the XGB classifier and outperform the RF, SVM, and PSETAE classifiers. Further, quantitative analysis of overall classification accuracies showed that Random Forest is the second-best performing classifier, and PSETAE classifier produced the lowest results for all data models.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101525"},"PeriodicalIF":3.8,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143686657","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":"Mapping oil palm expansion in the Eastern Amazon using optical and radar imagery","authors":"Pedro Henrique Batista de Barros ,&nbsp;Filipe Gomes Dias ,&nbsp;José Alberto Quintanilha ,&nbsp;Carlos Henrique Grohmann","doi":"10.1016/j.rsase.2025.101506","DOIUrl":"10.1016/j.rsase.2025.101506","url":null,"abstract":"<div><div>Palm oil, the world’s most widely consumed vegetable oil, plays a pivotal role in the food, biodiesel, and pharmaceutical industries. However, its rapid expansion in tropical regions has led to critical environmental challenges, including deforestation and biodiversity loss. This study maps oil palm plantations in the Eastern Amazon, Brazil’s largest producer, for 2014, 2017, and 2020, employing machine learning algorithms such as K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Decision Trees (DT), Support Vector Machines (SVM), and Random Forests (RF). This study integrate Landsat-8 optical spectral bands (blue, green, red, and near-infrared) with Sentinel-1 radar backscatter values (VV and VH polarizations) to map the expansion of oil palm in the Brazilian Amazon, a combination that has not been previously implemented in this region. Vegetation indices, including NDVI (Normalized Difference Vegetation Index), EVI (Enhanced Vegetation Index), SAVI (Soil-Adjusted Vegetation Index), DVI (Difference Vegetation Index), RVI (Ratio Vegetation Index), GI (Green Index), and texture indices derived from the gray-level co-occurrence matrix (GLCM), such as contrast, angular second moment (ASM), correlation, and entropy, were used to improve classification accuracy. A linear spectral mixing model was also applied to distinguish the spectral signatures, with the resulting end members subsequently incorporated. The RF achieved the highest classification accuracy, with overall accuracies of 94.53%, 94.28%, and 95.53% for 2014, 2017, and 2020, respectively. A land use and land cover (LULC) transition analysis revealed a substantial expansion of 72.16%, with the area growing from 1,074 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> in 2014 to 1,849 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> in 2020. Notably, 156.88 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> (20.24%) of this expansion occurred directly at the expense of vegetation cover, underscoring areas of significant environmental concern. This study offers valuable insights to guide the development of public and market-driven policies aimed at promoting sustainable and environmentally responsible oil palm expansion.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101506"},"PeriodicalIF":3.8,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643433","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":"Reconstructing the alarming fire history of Ankarafantsika National Park in northwestern Madagascar over a 35 year-period","authors":"Misa Rasolozaka ,&nbsp;Dominik Schüßler ,&nbsp;Johnny Randriafenontsoa ,&nbsp;Fenohery Andriatsitohaina ,&nbsp;Princia Rakotomamonjy ,&nbsp;Harison Rabarison ,&nbsp;Ute Radespiel","doi":"10.1016/j.rsase.2025.101521","DOIUrl":"10.1016/j.rsase.2025.101521","url":null,"abstract":"<div><div>The extent of fires in tropical ecosystems is highly dynamic, and responses of tropical dry forests to fire seem to vary and are not well understood. This study reconstructs a 35-year long fire history of the dry forests in the Ankarafantsika National Park (ANP) in Madagascar. In recent years, forest fires have been reported in this region, potentially threatening habitat integrity and connectivity inside ANP. We assessed the fire dynamics with yearly Landsat satellite images from 1988 to 2023 (Landsat 4–5, Landsat 7, Landsat 8–9) by means of the Normalized Burn Ratio (NBR) and the differenced NBR (dNBR) with a 30m resolution. To validate the fire classification in addition to exemplary ground truthing, 350 random points were selected across ANP and visually classified based on yearly Red Green Blue false-color composites and their corresponding dNBR images. Inside ANP, 70 % of the vegetation burnt at least once, while 18 % burnt even more than three times. Fire distribution was heterogenous with fires being more frequent in the north than in the south of ANP. The extent of burnt areas fluctuated over the years peaking in 2016 with 229 km² (22 % of the park vegetation). Fires recurred after 1–34 years, but more frequently than expected after 3–5 years. Areas requiring urgent conservation attention are highlighted and a baseline for developing fire management strategies is provided. Finally, this study demonstrates that ground truthing is essential to implement an analytical pipeline to correctly infer burnt and unburnt vegetation parts from series of satellite pictures.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"38 ","pages":"Article 101521"},"PeriodicalIF":3.8,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143686658","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}