Considering that seaweed gathering is a highly relevant socioeconomic activity in northern Chile, estimating available biomass is vital for its sustainable management. The direct and indirect evaluations used are difficult and untimely, apart from their high costs and imprecisions due to spatiotemporal resolution. This study aims at assessing the macroalgal biomass and its spatial distribution faster and more accurately for the resource's management. To do this, an indirect assessment model for the Lessonia Nigrescens biomass complex, which comprises photogrammetric surveys of multispectral images from unmanned aerial vehicles (UAVs) and their geoprocessing through geographical information systems (GIS), is proposed. Such geoprocessing includes a mathematical algorithm calibrated with in situ non-extractive sampling in order to indirectly get the macroalgal biomass of the areas under study. The model was applied in the Atacama and Coquimbo regions over winter and summer. Thematic layers were built through GIS, digital surface models and supervised classification, using the maximum likelihood method. The indirect biomass results obtained from the algorithm were correlated with the results of the biomass obtained from the direct sampling, showing an average association (R2) of 67 % in winter and 86 % in summer, and its spatial distribution with an accuracy of 70 % in winter and 73 % in summer. The model enabled to get the spatial distribution of the resource's biomass in the short term, displayed as geospatial databases and thematic cartography to support the decision making process in the sustainable management of this resource.
{"title":"A model for the macroalgal assessment of the Lessonia Nigrescens complex through unmanned aerial vehicles (UAV) and Geographic Information System (GIS)","authors":"Eduardo Manzano , Álvaro Pacheco , Carlos Manzano , Macarena Álvarez","doi":"10.1016/j.rsase.2025.101843","DOIUrl":"10.1016/j.rsase.2025.101843","url":null,"abstract":"<div><div>Considering that seaweed gathering is a highly relevant socioeconomic activity in northern Chile, estimating available biomass is vital for its sustainable management. The direct and indirect evaluations used are difficult and untimely, apart from their high costs and imprecisions due to spatiotemporal resolution. This study aims at assessing the macroalgal biomass and its spatial distribution faster and more accurately for the resource's management. To do this, an indirect assessment model for the <em>Lessonia Nigrescens</em> biomass complex, which comprises photogrammetric surveys of multispectral images from unmanned aerial vehicles (UAVs) and their geoprocessing through geographical information systems (GIS), is proposed. Such geoprocessing includes a mathematical algorithm calibrated with <em>in situ</em> non-extractive sampling in order to indirectly get the macroalgal biomass of the areas under study. The model was applied in the Atacama and Coquimbo regions over winter and summer. Thematic layers were built through GIS, digital surface models and supervised classification, using the maximum likelihood method. The indirect biomass results obtained from the algorithm were correlated with the results of the biomass obtained from the direct sampling, showing an average association (R<sup>2</sup>) of 67 % in winter and 86 % in summer, and its spatial distribution with an accuracy of 70 % in winter and 73 % in summer. The model enabled to get the spatial distribution of the resource's biomass in the short term, displayed as geospatial databases and thematic cartography to support the decision making process in the sustainable management of this resource.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101843"},"PeriodicalIF":4.5,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791456","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}
Pub Date : 2025-12-15DOI: 10.1016/j.rsase.2025.101833
Yu Lei, Lin Liu, Yuhuan Cui, Kerun Jiang, Shuang Hao
Rapid urban expansion in the Chaohu Lake Basin (Anhui Province, China) has profoundly altered the land use and ecosystem characteristics over the past two decades. This study investigates the spatiotemporal dynamics of this expansion and its coupled relationship with ecological sensitivity. Using Landsat imagery on the Google Earth Engine platform, we quantified land use and ecological sensitivity changes from 2000 to 2020. The land use change was dramatic, driven by urban expansion: the built-up area increased from 311.0 to 3885.9 km2, while cropland decreased by ∼41 % (4112.48 km2). Concurrently, the proportion of the ecologically insensitive areas (dominated by new built-up land) increased from 2.91 % to 28.35 % of the basin, while the extremely sensitive areas (protected forests and water bodies) remained at ∼4 %. Geodetector analysis revealed that land use type was the dominant driver (q > 0.75) of the spatial variations in ecological sensitivity. The coupling coordination modeling revealed a marked increase in the synergy between land use and ecological sensitivity, especially from 2010 to 2020. Overall, 45.8 % of the basin experienced improved coordination, underscoring that targeted land use planning and conservation policies can be effective in mitigating ecological pressure even during periods of rapid urbanization. These results clarify the co-evolution of urban-driven land use dynamics and ecological vulnerability, providing a scientific basis for achieving targeted ecological protection and sustainable development.
{"title":"Spatio-temporal dynamics and coupling of urban expansion with ecological sensitivity in Chaohu Lake Basin","authors":"Yu Lei, Lin Liu, Yuhuan Cui, Kerun Jiang, Shuang Hao","doi":"10.1016/j.rsase.2025.101833","DOIUrl":"10.1016/j.rsase.2025.101833","url":null,"abstract":"<div><div>Rapid urban expansion in the Chaohu Lake Basin (Anhui Province, China) has profoundly altered the land use and ecosystem characteristics over the past two decades. This study investigates the spatiotemporal dynamics of this expansion and its coupled relationship with ecological sensitivity. Using Landsat imagery on the Google Earth Engine platform, we quantified land use and ecological sensitivity changes from 2000 to 2020. The land use change was dramatic, driven by urban expansion: the built-up area increased from 311.0 to 3885.9 km<sup>2</sup>, while cropland decreased by ∼41 % (4112.48 km<sup>2</sup>). Concurrently, the proportion of the ecologically insensitive areas (dominated by new built-up land) increased from 2.91 % to 28.35 % of the basin, while the extremely sensitive areas (protected forests and water bodies) remained at ∼4 %. Geodetector analysis revealed that land use type was the dominant driver (q > 0.75) of the spatial variations in ecological sensitivity. The coupling coordination modeling revealed a marked increase in the synergy between land use and ecological sensitivity, especially from 2010 to 2020. Overall, 45.8 % of the basin experienced improved coordination, underscoring that targeted land use planning and conservation policies can be effective in mitigating ecological pressure even during periods of rapid urbanization. These results clarify the co-evolution of urban-driven land use dynamics and ecological vulnerability, providing a scientific basis for achieving targeted ecological protection and sustainable development.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101833"},"PeriodicalIF":4.5,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790941","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}
Desert Locust (DL) infestations pose a significant threat to food security in arid and semi-arid regions, particularly in East Africa, Central Asia, and the Indian subcontinent. In 2020, during the COVID-19 pandemic, India witnessed an unprecedented upsurge of DL activity during the summer (zaid) season (April–June), severely impacting Rajasthan, Gujarat, and neighbouring states. This study investigates the environmental drivers of the DL outbreak and assesses crop damage using geospatial datasets, reanalysis products, and numerical weather models. Fifteen grid cells (100 km × 100 km) along the DL-prone corridor from East Africa to India were analyzed for environmental suitability, with seasonal Spearman correlation analysis applied to identify significant factors influencing locust activity. In winter, locust activity was significantly positively correlated with rainfall (ρ = 0.47, p = 0.021), dew point temperature (ρ = 0.76, p = 0.01), and soil moisture (ρ = 0.50, p = 0.05), highlighting the importance of moisture and temperature conditions in facilitating locust presence. In spring, significant positive correlations were observed with air temperature (ρ = 0.56, p = 0.027), soil temperature 1 (ρ = 0.65, p = 0.01), and a very strong correlation with soil temperature 2 (ρ = 0.73, p = 0.002). These findings showed the crucial role of temperature and moisture during the winter and spring seasons as key drivers of locust behaviour. The Linear Discriminant Analysis (LDA) model shows potential in locust presence prediction, though challenges remain due to data limitations. Crop damage was quantified using Normalized Difference Vegetative Index (NDVI), showing severe vegetation loss in affected areas (NDVI <0.3) and degradation due to locust feeding. The study further integrates weather forecast wind patterns, MODIS Leaf Area Index (LAI), and soil moisture from SMAP to track locust migration. Wind patterns, particularly westerly and south-westerly winds, guided the locusts' entry into western India. Despite moderate LAI values, the vegetation cover in central and western India provided sufficient sustenance for the locusts. Soil moisture from SMAP consistently supported locust dispersal across northern Rajasthan, central India, and parts of Uttar Pradesh. The integration of these environmental factors offers a comprehensive understanding of DL behaviour, enhancing early warning and control efforts.
沙漠蝗对干旱和半干旱地区，特别是东非、中亚和印度次大陆的粮食安全构成重大威胁。2020年，在2019冠状病毒病大流行期间，印度在夏季（4月至6月）出现了前所未有的DL活动激增，严重影响了拉贾斯坦邦、古吉拉特邦和邻近邦。本研究利用地理空间数据集、再分析产品和数值天气模型调查了旱情暴发的环境驱动因素，并评估了作物损失。分析了东非至印度蝗灾易发走廊沿线15个网格单元（100 km × 100 km）的环境适宜性，并应用季节性Spearman相关分析确定了影响蝗灾活动的重要因素。在冬季，蝗虫活动与降雨量（ρ = 0.47, p = 0.021）、露点温度（ρ = 0.76, p = 0.01）和土壤湿度（ρ = 0.50, p = 0.05）呈显著正相关，突出了湿度和温度条件对促进蝗虫存在的重要性。春季与气温（ρ = 0.56, p = 0.027）、土壤温度（ρ = 0.65, p = 0.01）呈极显著正相关，与土壤温度（ρ = 0.73, p = 0.002）呈极强相关。这些发现表明，冬季和春季的温度和湿度是蝗虫行为的关键驱动因素。线性判别分析（LDA）模型显示了蝗虫存在预测的潜力，尽管由于数据限制仍然存在挑战。利用归一化植被指数（NDVI）对作物损害进行量化，显示受蝗灾影响地区植被损失严重（NDVI <0.3），且因蝗虫取食而退化。该研究进一步结合天气预报风向、MODIS叶面积指数（LAI）和SMAP的土壤湿度来跟踪蝗虫的迁移。风向，特别是西风和西南风，引导蝗虫进入印度西部。尽管LAI值适中，但印度中部和西部的植被覆盖为蝗虫提供了足够的食物。SMAP的土壤湿度持续支持蝗虫在拉贾斯坦邦北部、印度中部和北方邦部分地区的扩散。这些环境因素的整合提供了对深度学习行为的全面理解，加强了早期预警和控制工作。
{"title":"A geo-spatial assessment of desert locust risk over India during summer 2020 using GEO-LEO satellite observations and weather forecast","authors":"Rahul Nigam, Bimal K. Bhattacharya, Ayan Das, Mukesh Kumar, Prashant Kumar","doi":"10.1016/j.rsase.2025.101831","DOIUrl":"10.1016/j.rsase.2025.101831","url":null,"abstract":"<div><div>Desert Locust (DL) infestations pose a significant threat to food security in arid and semi-arid regions, particularly in East Africa, Central Asia, and the Indian subcontinent. In 2020, during the COVID-19 pandemic, India witnessed an unprecedented upsurge of DL activity during the summer (zaid) season (April–June), severely impacting Rajasthan, Gujarat, and neighbouring states. This study investigates the environmental drivers of the DL outbreak and assesses crop damage using geospatial datasets, reanalysis products, and numerical weather models. Fifteen grid cells (100 km × 100 km) along the DL-prone corridor from East Africa to India were analyzed for environmental suitability, with seasonal Spearman correlation analysis applied to identify significant factors influencing locust activity. In winter, locust activity was significantly positively correlated with rainfall (ρ = 0.47, p = 0.021), dew point temperature (ρ = 0.76, p = 0.01), and soil moisture (ρ = 0.50, p = 0.05), highlighting the importance of moisture and temperature conditions in facilitating locust presence. In spring, significant positive correlations were observed with air temperature (ρ = 0.56, p = 0.027), soil temperature 1 (ρ = 0.65, p = 0.01), and a very strong correlation with soil temperature 2 (ρ = 0.73, p = 0.002). These findings showed the crucial role of temperature and moisture during the winter and spring seasons as key drivers of locust behaviour. The Linear Discriminant Analysis (LDA) model shows potential in locust presence prediction, though challenges remain due to data limitations. Crop damage was quantified using Normalized Difference Vegetative Index (NDVI), showing severe vegetation loss in affected areas (NDVI <0.3) and degradation due to locust feeding. The study further integrates weather forecast wind patterns, MODIS Leaf Area Index (LAI), and soil moisture from SMAP to track locust migration. Wind patterns, particularly westerly and south-westerly winds, guided the locusts' entry into western India. Despite moderate LAI values, the vegetation cover in central and western India provided sufficient sustenance for the locusts. Soil moisture from SMAP consistently supported locust dispersal across northern Rajasthan, central India, and parts of Uttar Pradesh. The integration of these environmental factors offers a comprehensive understanding of DL behaviour, enhancing early warning and control efforts.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101831"},"PeriodicalIF":4.5,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791462","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}
Pub Date : 2025-12-14DOI: 10.1016/j.rsase.2025.101840
Reddy R. Pullanagari , Mohammad Hossain Dehghan-Shoar , Junqi Zhu , Alvaro A. Orsi , Ian J. Yule
Sun-induced chlorophyll fluorescence (SIF) has emerged as a valuable proxy for estimating plant physiological activity. While empirical and one-dimensional (1D) radiative transfer models (RTMs) have shown reasonable success in quantifying SIF at the canopy scale using hyperspectral sensors, they face challenges in addressing complex, heterogeneous canopy structures, weak signals, and intricate sun-to-sensor geometries. In recent years, three-dimensional (3D) RTMs have made significant progress in overcoming these challenges.
This study employed multiple RTMs, such as PROSPECT-PRO, FLUSPECT, and LESS, to investigate SIF in kiwifruit orchards. High-resolution hyperspectral imagery and LiDAR data were collected over the orchards, along with ground-truth measurements. A 3D kiwifruit canopy was reconstructed using functional-structural plant modeling (FSPM) based on LiDAR point cloud data. Utilizing the LESS RTM, thousands of reflectance spectra were simulated based on the given leaf and soil optical properties and the 3D canopy structure.
A kernel ridge regression (KRR) algorithm was trained on these simulations in the SIF region (650–810 nm) and validated with the ground-truth measurements. This hybrid (3D RTM-KRR) model demonstrated a high correlation with the ground-truth data, outperforming empirical models (such as Fraunhofer line discrimination methods). This indicates its capability to extract SIF from coarse-resolution airborne and satellite-based hyperspectral missions (e.g., PRISMA and EnMAP). This approach offers a promising avenue for improving our understanding of plant physiological processes and their interactions with the environment at larger scales. This research provides a significant advancement for precision agriculture in orchards, proving the practical value of 3D RTM for heterogeneous canopies.
{"title":"Mapping of sun-induced fluorescence (SIF) in kiwifruit canopy using a 3D radiative transfer modeling and airborne hyperspectral imaging","authors":"Reddy R. Pullanagari , Mohammad Hossain Dehghan-Shoar , Junqi Zhu , Alvaro A. Orsi , Ian J. Yule","doi":"10.1016/j.rsase.2025.101840","DOIUrl":"10.1016/j.rsase.2025.101840","url":null,"abstract":"<div><div>Sun-induced chlorophyll fluorescence (SIF) has emerged as a valuable proxy for estimating plant physiological activity. While empirical and one-dimensional (1D) radiative transfer models (RTMs) have shown reasonable success in quantifying SIF at the canopy scale using hyperspectral sensors, they face challenges in addressing complex, heterogeneous canopy structures, weak signals, and intricate sun-to-sensor geometries. In recent years, three-dimensional (3D) RTMs have made significant progress in overcoming these challenges.</div><div>This study employed multiple RTMs, such as PROSPECT-PRO, FLUSPECT, and LESS, to investigate SIF in kiwifruit orchards. High-resolution hyperspectral imagery and LiDAR data were collected over the orchards, along with ground-truth measurements. A 3D kiwifruit canopy was reconstructed using functional-structural plant modeling (FSPM) based on LiDAR point cloud data. Utilizing the LESS RTM, thousands of reflectance spectra were simulated based on the given leaf and soil optical properties and the 3D canopy structure.</div><div>A kernel ridge regression (KRR) algorithm was trained on these simulations in the SIF region (650–810 nm) and validated with the ground-truth measurements. This hybrid (3D RTM-KRR) model demonstrated a high correlation with the ground-truth data, outperforming empirical models (such as Fraunhofer line discrimination methods). This indicates its capability to extract SIF from coarse-resolution airborne and satellite-based hyperspectral missions (e.g., PRISMA and EnMAP). This approach offers a promising avenue for improving our understanding of plant physiological processes and their interactions with the environment at larger scales. This research provides a significant advancement for precision agriculture in orchards, proving the practical value of 3D RTM for heterogeneous canopies.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101840"},"PeriodicalIF":4.5,"publicationDate":"2025-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840886","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}
Pub Date : 2025-12-13DOI: 10.1016/j.rsase.2025.101836
Aleksi Isoaho , Timo P. Pitkänen , Lauri Ikkala , Antti Sallinen , Parvez Rana , Hannu Marttila , Lassi Päkkilä , Aleksi Räsänen
Remote sensing (RS) methods are recognized as a potential solution for the increasing need to monitor peatland changes after restoration, but practical monitoring tools are lacking. To address this gap, our objective is to (1) test which optical satellite variables can be used for detecting hydrological restoration impact in treeless boreal peatlands, (2) develop a user-friendly Google Earth Engine (GEE) application based on the results, and (3) demonstrate its usage in practice. Firstly, by utilizing data from 24 peatland restoration sites in Finland, we used Mann-Whitney U test and Kruskal-Wallis test to determine which optical variables calculated from Sentinel-2 and Landsat 8–9 satellite imagery can be used as indicators for surface wetness changes after peatland restoration. The results from statistical tests indicated that near-infrared (NIR) and shortwave infrared (SWIR) bands were the most effective in detecting the impact. Secondly, we incorporated the NIR and SWIR bands into the GEE application to indicate the location and magnitude of restoration impact. The developed application uses a direct input from the openly available satellite imagery archives and requires only a few inputs from the user for the case-specific analysis, making it user-friendly. The application calculates cloudless and representative satellite image mosaics and uses change detection for the situations before and after restoration to show the hydrological restoration impacts spatially. The application provides researchers, stakeholders, decision-makers, and practitioners with limited technical experience the possibility to use satellite imagery for assessing restoration impacts in open or sparsely treed peatlands in boreal landscapes.
{"title":"An automated Google Earth Engine application for detecting the impacted area of treeless boreal peatland restoration – A tool for practitioners and decision-makers","authors":"Aleksi Isoaho , Timo P. Pitkänen , Lauri Ikkala , Antti Sallinen , Parvez Rana , Hannu Marttila , Lassi Päkkilä , Aleksi Räsänen","doi":"10.1016/j.rsase.2025.101836","DOIUrl":"10.1016/j.rsase.2025.101836","url":null,"abstract":"<div><div>Remote sensing (RS) methods are recognized as a potential solution for the increasing need to monitor peatland changes after restoration, but practical monitoring tools are lacking. To address this gap, our objective is to (1) test which optical satellite variables can be used for detecting hydrological restoration impact in treeless boreal peatlands, (2) develop a user-friendly Google Earth Engine (GEE) application based on the results, and (3) demonstrate its usage in practice. Firstly, by utilizing data from 24 peatland restoration sites in Finland, we used Mann-Whitney <em>U</em> test and Kruskal-Wallis test to determine which optical variables calculated from Sentinel-2 and Landsat 8–9 satellite imagery can be used as indicators for surface wetness changes after peatland restoration. The results from statistical tests indicated that near-infrared (NIR) and shortwave infrared (SWIR) bands were the most effective in detecting the impact. Secondly, we incorporated the NIR and SWIR bands into the GEE application to indicate the location and magnitude of restoration impact. The developed application uses a direct input from the openly available satellite imagery archives and requires only a few inputs from the user for the case-specific analysis, making it user-friendly. The application calculates cloudless and representative satellite image mosaics and uses change detection for the situations before and after restoration to show the hydrological restoration impacts spatially. The application provides researchers, stakeholders, decision-makers, and practitioners with limited technical experience the possibility to use satellite imagery for assessing restoration impacts in open or sparsely treed peatlands in boreal landscapes.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101836"},"PeriodicalIF":4.5,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790939","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}
Pub Date : 2025-12-13DOI: 10.1016/j.rsase.2025.101834
Anagha S. Dhavalikar
Oil spill detection is a crucial component of marine environmental protection and disaster management. Remote sensing technologies, using Synthetic Aperture Radar (SAR) imagery, offer a consistent and robust method for identifying and monitoring oil spills. In this study, transfer learning is employed to adapt three state-of-the-art deep convolutional neural networks (CNNs)—ResNet18, ResNet50, and EfficientNet-B0 which are pretrained on the ImageNet dataset, to the binary classification task of identifying oil spills and look-alikes in SAR images. With a balanced dataset having 278 images of oil spill and 262 of look-alike classes, across 10 epochs, ResNet18, ResNet50, and EfficientNet-B0 achieved high training accuracies in the range of 95–97 %. ResNet50 showed the best validation accuracy of 87.86 % and Test Accuracy 84.05 %. EfficientNet-B0, while lighter and faster, had slightly lower validation performance. ResNet18 offers a balance between speed and accuracy, whereas ResNet50 is optimal for accuracy if resources permit.
{"title":"Enhanced transfer learning for marine oil spill pollution monitoring","authors":"Anagha S. Dhavalikar","doi":"10.1016/j.rsase.2025.101834","DOIUrl":"10.1016/j.rsase.2025.101834","url":null,"abstract":"<div><div>Oil spill detection is a crucial component of marine environmental protection and disaster management. Remote sensing technologies, using Synthetic Aperture Radar (SAR) imagery, offer a consistent and robust method for identifying and monitoring oil spills. In this study, transfer learning is employed to adapt three state-of-the-art deep convolutional neural networks (CNNs)—ResNet18, ResNet50, and EfficientNet-B0 which are pretrained on the ImageNet dataset, to the binary classification task of identifying oil spills and look-alikes in SAR images. With a balanced dataset having 278 images of oil spill and 262 of look-alike classes, across 10 epochs, ResNet18, ResNet50, and EfficientNet-B0 achieved high training accuracies in the range of 95–97 %. ResNet50 showed the best validation accuracy of 87.86 % and Test Accuracy 84.05 %. EfficientNet-B0, while lighter and faster, had slightly lower validation performance. ResNet18 offers a balance between speed and accuracy, whereas ResNet50 is optimal for accuracy if resources permit.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101834"},"PeriodicalIF":4.5,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790940","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}
Pub Date : 2025-12-13DOI: 10.1016/j.rsase.2025.101825
Roberto Calisti , Luca Regni , Raffaella Brigante , Laura Marconi , Alessandra Vinci , Fabio Radicioni , Primo Proietti
The olive groves, particularly the old ones, represent a significant carbon sink and so they are important for climate change mitigation. Also, many of these olive groves represent an important component of the landscape heritage. This study focuses on estimating biomass and carbon content in old olive tree groves, with a specific application in a 69-year-old olive grove in central Italy. The research used UAV (Unmanned Aerial Vehicle) survey data to evaluate the geometric features of some selected olive trees, using LiDAR (Light Detection and Ranging) and manual survey as basis for comparison and benchmark. The aim was to determine the effectiveness of UAV method, which this study showed to be less costly, less time-consuming, and less prone to drawbacks compared to the LiDAR and manual measurements. After felling the olive trees, their epigeal biomass was weighed. A strong linear correlation was found between the geometric parameters (trunk circumference, crown area, and crown volume) and the fresh weight of the trees. The results of this study show that UAV surveying provides a viable solution for assessing the carbon content of old olive groves, representing a significant improvement in relation to the methods still proposed by the IPCC (Intergovernmental Panel on Climate Change). As with all other proposed methods, the main issue concerns the estimation of the belowground biomass, for which there are currently no methods with a low degree of uncertainty, so there is a need to develop more accurate models.
橄榄林，尤其是老的橄榄林，代表着一个重要的碳汇，因此它们对减缓气候变化很重要。此外，许多橄榄园是景观遗产的重要组成部分。本研究的重点是估算老橄榄树林的生物量和碳含量，并在意大利中部一个69岁的橄榄树林中进行了具体应用。本研究利用无人机（UAV）调查数据对部分选定的橄榄树进行几何特征评价，以LiDAR （Light Detection and Ranging）和人工调查作为对比基准。目的是确定无人机方法的有效性，该研究表明，与激光雷达和手动测量相比，无人机方法成本更低，耗时更短，并且不易出现缺陷。采伐橄榄树后，对其表皮生物量进行称重。几何参数（树干周长、树冠面积和树冠体积）与树鲜重呈较强的线性相关。本研究结果表明，无人机测量为评估老橄榄园的碳含量提供了一个可行的解决方案，与IPCC（政府间气候变化专门委员会）仍然提出的方法相比，这是一个显著的改进。与所有其他提出的方法一样，主要问题涉及地下生物量的估计，目前还没有具有低不确定性的方法，因此需要开发更准确的模型。
{"title":"Estimating carbon storage in an old olive tree grove: A comparison of UAV, LiDAR, and manual surveys","authors":"Roberto Calisti , Luca Regni , Raffaella Brigante , Laura Marconi , Alessandra Vinci , Fabio Radicioni , Primo Proietti","doi":"10.1016/j.rsase.2025.101825","DOIUrl":"10.1016/j.rsase.2025.101825","url":null,"abstract":"<div><div>The olive groves, particularly the old ones, represent a significant carbon sink and so they are important for climate change mitigation. Also, many of these olive groves represent an important component of the landscape heritage. This study focuses on estimating biomass and carbon content in old olive tree groves, with a specific application in a 69-year-old olive grove in central Italy. The research used UAV (Unmanned Aerial Vehicle) survey data to evaluate the geometric features of some selected olive trees, using LiDAR (Light Detection and Ranging) and manual survey as basis for comparison and benchmark. The aim was to determine the effectiveness of UAV method, which this study showed to be less costly, less time-consuming, and less prone to drawbacks compared to the LiDAR and manual measurements. After felling the olive trees, their epigeal biomass was weighed. A strong linear correlation was found between the geometric parameters (trunk circumference, crown area, and crown volume) and the fresh weight of the trees. The results of this study show that UAV surveying provides a viable solution for assessing the carbon content of old olive groves, representing a significant improvement in relation to the methods still proposed by the IPCC (Intergovernmental Panel on Climate Change). As with all other proposed methods, the main issue concerns the estimation of the belowground biomass, for which there are currently no methods with a low degree of uncertainty, so there is a need to develop more accurate models.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101825"},"PeriodicalIF":4.5,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791458","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}
Pub Date : 2025-12-12DOI: 10.1016/j.rsase.2025.101829
Kishore Bhamidipati , M. Kaur , Tarandeep Singh Walia , D. Garg , Mohammed Amoon , Ekasnh Bhardwaj , Robertas Damaševičius
Pansharpening plays an important role in improving the spatial resolution of multispectral images while preserving their spectral information. It enables more detailed and accurate analysis in various applications, such as remote sensing and environmental monitoring. Recent advances in deep learning-based pansharpening models have resulted in substantial improvements in performance. However, these models still suffer from the balancing of spectral accuracy and spatial detail, which can lead to artifacts, quality degradation, and overfitting problems. To overcome these limitations, an efficient pansharpening model is proposed. Initially, a dual transformer block is designed which integrates Swin and DeiT transformers to improve both local and global feature extraction. These features are then processed through a proposed U-shaped encoder–decoder network. This network utilizes the dual transformer block in both encoding and decoding stages. Finally, a customized multi-aspect pansharpening loss (MAPL) is introduced to preserve spectral fidelity, enhance spatial resolution, and improve perceptual quality. Extensive experimental results demonstrate that the proposed model significantly outperforms competitive models on various performance metrics. Thus, compared to competitive models, the proposed model shows significant improvements in preserving fine spatial details and maintaining spectral accuracy.
{"title":"Hybrid dual-transformer pansharpening network for enhanced spatial-spectral fidelity","authors":"Kishore Bhamidipati , M. Kaur , Tarandeep Singh Walia , D. Garg , Mohammed Amoon , Ekasnh Bhardwaj , Robertas Damaševičius","doi":"10.1016/j.rsase.2025.101829","DOIUrl":"10.1016/j.rsase.2025.101829","url":null,"abstract":"<div><div>Pansharpening plays an important role in improving the spatial resolution of multispectral images while preserving their spectral information. It enables more detailed and accurate analysis in various applications, such as remote sensing and environmental monitoring. Recent advances in deep learning-based pansharpening models have resulted in substantial improvements in performance. However, these models still suffer from the balancing of spectral accuracy and spatial detail, which can lead to artifacts, quality degradation, and overfitting problems. To overcome these limitations, an efficient pansharpening model is proposed. Initially, a dual transformer block is designed which integrates Swin and DeiT transformers to improve both local and global feature extraction. These features are then processed through a proposed U-shaped encoder–decoder network. This network utilizes the dual transformer block in both encoding and decoding stages. Finally, a customized multi-aspect pansharpening loss (MAPL) is introduced to preserve spectral fidelity, enhance spatial resolution, and improve perceptual quality. Extensive experimental results demonstrate that the proposed model significantly outperforms competitive models on various performance metrics. Thus, compared to competitive models, the proposed model shows significant improvements in preserving fine spatial details and maintaining spectral accuracy.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101829"},"PeriodicalIF":4.5,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791459","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}
Pub Date : 2025-12-12DOI: 10.1016/j.rsase.2025.101823
Mohammed Q. Alkhatib , Ali Jamali
Over the past decade, hyperspectral image (HSI) classification has drawn considerable interest due to HSIs’ ability to effectively distinguish terrestrial objects by capturing detailed, continuous spectral information. The strong performance of recent deep learning techniques in tasks like image classification and semantic segmentation has led to their growing use in HSI classification, due to their ability to capture complex spatial and spectral features more effectively than traditional methods. This paper presents MixerCA, a novel lightweight model for HSI classification that leverages depthwise convolution and a self-attention mechanism. MixerCA integrates depth-wise convolutions, token and channel mixing, and coordinate attention into a unified structure to decouple spatial and channel interactions, maintain consistent resolution throughout the network, and directly process HSI patches. Extensive experiments on four hyperspectral benchmark datasets reveal MixerCA’s clear advantages over several competing algorithms, including 2D-CNN, 3D-CNN, Tri-CNN, HybridSN, ViT, and Swin Transformer. The source code is publicly available at https://github.com/mqalkhatib/MixerCA.
{"title":"MixerCA: An efficient and accurate model for high-performance hyperspectral image classification","authors":"Mohammed Q. Alkhatib , Ali Jamali","doi":"10.1016/j.rsase.2025.101823","DOIUrl":"10.1016/j.rsase.2025.101823","url":null,"abstract":"<div><div>Over the past decade, hyperspectral image (HSI) classification has drawn considerable interest due to HSIs’ ability to effectively distinguish terrestrial objects by capturing detailed, continuous spectral information. The strong performance of recent deep learning techniques in tasks like image classification and semantic segmentation has led to their growing use in HSI classification, due to their ability to capture complex spatial and spectral features more effectively than traditional methods. This paper presents MixerCA, a novel lightweight model for HSI classification that leverages depthwise convolution and a self-attention mechanism. MixerCA integrates depth-wise convolutions, token and channel mixing, and coordinate attention into a unified structure to decouple spatial and channel interactions, maintain consistent resolution throughout the network, and directly process HSI patches. Extensive experiments on four hyperspectral benchmark datasets reveal MixerCA’s clear advantages over several competing algorithms, including 2D-CNN, 3D-CNN, Tri-CNN, HybridSN, ViT, and Swin Transformer. The source code is publicly available at <span><span>https://github.com/mqalkhatib/MixerCA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101823"},"PeriodicalIF":4.5,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790942","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}
Pub Date : 2025-12-12DOI: 10.1016/j.rsase.2025.101838
Axel Belemtougri , Roland Yonaba , Claire I. Michailovsky , Tibor Stigter , Lawani Adjadi Mounirou , Pieter van der Zaag
This study presents a new geospatial framework for detecting and mapping ephemeral sand rivers (ESRs) across the West African Sahel, focusing on Burkina Faso, Mali, and Niger, where food security challenges are acute. ESRs, which remain dry most of the year, act as vital subsurface water reservoirs in arid environments. During the wet season, infiltrated streamflow is stored within sandy beds, minimizing evaporative losses and providing shallow groundwater with potential to support domestic, livestock, and agricultural needs during dry periods. The methodology integrates hydrological analyses, remote sensing, and machine learning. A high-resolution drainage network was derived from the 90 m MERIT DEM, based on national reference river networks and satellite-derived information. A Random Forest model predicted river flow intermittency and identified ephemeral rivers (flowing 1–4 months annually, catchment area ≥1000 km2), around which 500 m buffer zones were delineated for analysis. Two composite thresholds (CTs) combining NDESI–NDVI spectral indices achieved moderate accuracy: CT1 (42 %) and CT2 (72 %), with CT2 serving as a first-order tool for sandy riverbed detection. A multi-temporal supervised land use/land cover classification achieved high accuracy (92 %) and F1 scores >0.86, outperforming the spectral thresholds. Using vegetation presence as a proxy for shallow groundwater, 19 % of ESRs (402 km) were identified as areas of potentially accessible water storage near settlements representing about 3 million people (4.8 % of the population) across the three countries. These findings highlight the importance of ESRs for sustainable water management and climate-resilient livelihoods in the Sahel.
本研究提出了一个新的地理空间框架，用于探测和绘制整个西非萨赫勒地区的短暂沙河（ESRs），重点关注粮食安全挑战严峻的布基纳法索、马里和尼日尔。esr在一年中大部分时间保持干燥，在干旱环境中充当重要的地下水库。在雨季，渗透的水流被储存在沙质河床中，最大限度地减少蒸发损失，并提供浅层地下水，有可能在干旱时期支持家庭、牲畜和农业需求。该方法集成了水文分析、遥感和机器学习。基于国家参考河网和卫星衍生信息，从90 m MERIT DEM中获得了一个高分辨率的排水网络。随机森林模型预测了河流的间歇性，并确定了短暂河流（每年流动1-4个月，集水区面积≥1000 km2），并在其周围划定了500 m缓冲区进行分析。结合NDESI-NDVI光谱指数的两个复合阈值（ct）达到了中等精度：CT1（42%）和CT2(72%)，其中CT2作为砂质河床检测的一级工具。一个多时间监督的土地利用/土地覆盖分类获得了很高的准确性（92%），F1得分>；0.86，优于光谱阈值。使用植被存在作为浅层地下水的代表，19%的esr（402公里）被确定为潜在的可达储水区域，靠近三个国家约300万人口（占人口的4.8%）的定居点。这些发现突出了可持续水资源管理和气候适应型生计在萨赫勒地区的重要性。
{"title":"Where rivers sleep: mapping ephemeral sand rivers in the West African Sahel","authors":"Axel Belemtougri , Roland Yonaba , Claire I. Michailovsky , Tibor Stigter , Lawani Adjadi Mounirou , Pieter van der Zaag","doi":"10.1016/j.rsase.2025.101838","DOIUrl":"10.1016/j.rsase.2025.101838","url":null,"abstract":"<div><div>This study presents a new geospatial framework for detecting and mapping ephemeral sand rivers (ESRs) across the West African Sahel, focusing on Burkina Faso, Mali, and Niger, where food security challenges are acute. ESRs, which remain dry most of the year, act as vital subsurface water reservoirs in arid environments. During the wet season, infiltrated streamflow is stored within sandy beds, minimizing evaporative losses and providing shallow groundwater with potential to support domestic, livestock, and agricultural needs during dry periods. The methodology integrates hydrological analyses, remote sensing, and machine learning. A high-resolution drainage network was derived from the 90 m MERIT DEM, based on national reference river networks and satellite-derived information. A Random Forest model predicted river flow intermittency and identified ephemeral rivers (flowing 1–4 months annually, catchment area ≥1000 km<sup>2</sup>), around which 500 m buffer zones were delineated for analysis. Two composite thresholds (CTs) combining NDESI–NDVI spectral indices achieved moderate accuracy: CT1 (42 %) and CT2 (72 %), with CT2 serving as a first-order tool for sandy riverbed detection. A multi-temporal supervised land use/land cover classification achieved high accuracy (92 %) and F1 scores >0.86, outperforming the spectral thresholds. Using vegetation presence as a proxy for shallow groundwater, 19 % of ESRs (402 km) were identified as areas of potentially accessible water storage near settlements representing about 3 million people (4.8 % of the population) across the three countries. These findings highlight the importance of ESRs for sustainable water management and climate-resilient livelihoods in the Sahel.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101838"},"PeriodicalIF":4.5,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790938","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号