<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Frontiers in Remote Sensing | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/remote-sensing</link>
        <description>RSS Feed for Frontiers in Remote Sensing | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-09-28T17:26:54.897+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1908768</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1908768</link>
        <title><![CDATA[Cross-sensor urban land-cover characterization using hyperspectral and multispectral satellite imagery]]></title>
        <pubdate>2026-09-23T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Sawaid Abbas</author><author> Zohaib</author><author>Nawai Habib</author><author>Faisal Mueen Qamer</author><author>Majid Nazeer</author>
        <description><![CDATA[IntroductionThis study establishes a cross-sensor urban remote sensing baseline for future urban digital-intelligence applications by integrating separately classified and validated multispectral (Landsat, Sentinel-2) and hyperspectral (PRISMA) imagery using a common sampling and evaluation framework.Methods Eight land-cover classes — Dense Urban Area, Medium Urban Area, Sparse Urban Area, Tree Cover, Grass, Cropland, Bare Area, and Water — were mapped using Random Forest, Support Vector Machine (SVM), Gradient Boosting Machine, K-Nearest Neighbor, and Classification and Regression Tree algorithms. Performance was evaluated across all three sensors using overall accuracy, Cohen’s kappa, macro-averaged and class-wise F1-scores, class-area composition, spectral profile, Fisher scores, pairwise separability metrics, and principal component analysis (PCA).ResultsResults demonstrated clear sensor-dependent differences in urban representation and classification accuracy. Sentinel-2 improved spatial characterization of heterogeneous urban surfaces through enhanced spatial resolution and red-edge information. PRISMA produced the highest classification performance, with SVM achieving an overall accuracy of 91.26% and a macro-averaged F1-score of 89.72%. However, this advantage was class-specific rather than uniform across all urban-density classes. Spectral-profile and PCA analysis showed hyperspectral observations substantially improved separability between Medium and Sparse Urban classes (spectral angle: 0.54° Landsat, 1.58° Sentinel-2, 4.11° PRISMA). PRISMA classifications also allocated substantially less area to Sparse Urban Area and more to Bare Area than the multispectral classifications.DiscussionThis redistribution may reflect improved discrimination of mixed peri-urban surfaces but cannot be considered more accurate without an independent concurrent area-wide reference map. The findings do not establish universal sensor superiority; rather classification outcomes depend jointly on sensor properties, acquisition timing, preprocessing, class definitions, and classifier choice, supporting a complementary interpretation of multispectral and hyperspectral observations.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1860441</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1860441</link>
        <title><![CDATA[Leveraging Sentinel-2 and Sentinel-1 imagery for retrieving key wheat phenology stages in a dryland agricultural setting]]></title>
        <pubdate>2026-09-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ahmed S. Almalki</author><author>Marcel M. El Hajj</author><author>Kasper Johansen</author><author>Matthew F. McCabe</author>
        <description><![CDATA[Monitoring crop phenology is crucial for agricultural management, providing the basis for timely decisions related to irrigation and fertilization, while offering insights into crop condition. This is particularly important in drylands, where agriculture is constrained by water scarcity and harsh environmental conditions, making phenology monitoring essential for optimizing resources and sustaining productivity. Despite its importance, traditional ground-based phenology monitoring methods are limited in scalability and consistency, underscoring the need for satellite-based alternatives. In this study, we investigated the feasibility of using time-series data from Sentinel-2 and Sentinel-1 imagery, each analyzed separately and combined with curve-based rules (i.e., threshold- or inflection-point criteria applied to temporal profiles), to retrieve five phenology stages of germination date, flowering date, senescence date, harvesting date, and cycle length for a large number of wheat fields in the Al-Jouf region of Saudi Arabia, a hot desert environment receiving less than 100 mm of annual precipitation that typifies dryland agriculture. To achieve this, we used 85 cloud-free Sentinel-2 and 94 Sentinel-1 images, along with in situ phenology observations. From Sentinel-2 imagery, we derived the normalized difference vegetation index (NDVI), green-red vegetation index (GRVI), and plant senescence reflectance index (PSRI), while volume backscattering (VV-VH), i.e., difference between vertical transmit/vertical receive (VV) and vertical transmit/horizontal receive (VH), was derived from Sentinel-1 imagery. Field-level time-series of each Sentinel-2 and Sentinel-1 metric were extracted and fitted with Gaussian functions. Next, the five phenology stages were retrieved by applying stage-specific curve-based rules to Gaussian-fitted field-level time-series of each metric. The accuracy of retrievals was assessed against in situ observations. Results showed that curve-based rules applied to NDVI, GRVI, and PSRI provided relative root mean square error (rRMSE) values of 2.64%–14.17% and bias magnitudes of 7.34–20.60 days across all stages without requiring rule refinement. Rules applied to VV-VH produced rRMSE values of 4.60%–26.22% and bias magnitudes of 7.11–43.73 days. Targeted refinement of flowering and harvesting rules reduced these errors. Overall, this work demonstrates the effectiveness of applying curve-based rules to each of Sentinel-2 and Sentinel-1 data separately in the dryland setting examined here, providing a foundation for evaluation across the broader range of drylands.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1941508</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1941508</link>
        <title><![CDATA[Diminishing aerosol-related compensation of vegetation productivity across China: asymmetric responses of AGC, LAI, NPP, and GPP from 2002 to 2020]]></title>
        <pubdate>2026-09-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ruige Dong</author><author>Xiangyuan Duan</author><author>Chencheng Yin</author><author>Meng Zhang</author><author>Wenping Jin</author><author>Yuan Zhang</author>
        <description><![CDATA[The mechanisms and influencing factors of changes in vegetation productivity have always been a global concern. Current research focuses on how precipitation, temperature, and human activities affect vegetation productivity. Atmospheric aerosols scatter and absorb solar radiation, which affects the terrestrial radiation balance, surface temperature, and water cycle, thereby indirectly affecting vegetation productivity. However, the statistical responses of vegetation productivity to dynamic changes in atmospheric aerosols, particularly their potential asymmetric characteristics, remain insufficiently understood. Therefore, this paper used the asymmetry index (AI) to analyze the asymmetric response of four vegetation productivity parameters to the dynamic changes of aerosol optical depth (AOD) in China from 2002 to 2020 and discussed the response under different vegetation types and environmental conditions. The results indicate that the asymmetric response of vegetation productivity to AOD is widespread and spatially heterogeneous. Regions in northeastern, eastern, and central China displayed a negative asymmetric response, which demonstrated that the negative impact of high AOD on vegetation productivity surpassed the positive impact of low AOD, resulting in losses outweighing gains. During the study period, the positive asymmetry shifted to a negative asymmetry, as shown by the decreasing AI. Notably, the AI of the four vegetation productivity parameters all peaked around 2008–2013, indicating vegetation productivity had its strongest compensatory effect. Grassland and cropland productivity exhibit pronounced sensitivity to atmospheric aerosol variations, whereas forest ecosystems demonstrate relatively muted responses. In areas with higher precipitation or temperature, the negative asymmetric response of vegetation productivity to AOD gradually increases. In contrast, vegetation productivity gradually shows a positive asymmetric response trend as altitude increases. This study reveals the asymmetric responses of vegetation productivity to aerosol changes and the differentiation patterns of these responses along environmental gradients, offering new insights for research on ecosystem–atmosphere interactions.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1698781</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1698781</link>
        <title><![CDATA[Deep learning-based classification of wet direct seeded rice, broadcasted direct seeded rice and transplanted rice using drone imagery for precision agriculture]]></title>
        <pubdate>2026-09-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Amrutha Lakshmi Gubbala</author><author>Santosha Rathod</author><author>Ramesh Dasyam</author><author>Mahender Kumar Rapolu</author><author>Arun Kumar Dasari</author><author>Pundarikakshudu Kurra</author><author>Hanuma Raviteja Madireddy</author><author>Prajwal R. Shashishekhar</author><author>Ravi V. Mural</author><author>Anil Kumar</author><author>Raman Meenakshi Sundaram</author>
        <description><![CDATA[Accurate estimation of crop area using classification techniques applied to drone imagery plays an important role in precision agriculture. Traditional machine learning (ML) approaches have been widely used for agricultural image classification; however, advanced deep learning (DL) models generally provide superior feature extraction and classification capability for complex crop patterns. Differentiating various rice establishment methods is essential for precise area estimation. In this study, advanced deep learning models were employed to classify three types of rice cultivation: (i) Broadcasted Direct Seeded Rice (DSR), (ii) Wet Direct Seeded Rice (Wet DSR), and (iii) Transplanted Rice (TR) using drone imagery. The drone imagery was collected from an experimental field at Praanadhaara Organised Agro Forestry Private Limited, Bapatla District, Andhra Pradesh, India. The images were captured in the visible spectrum (Red, Green, and Blue bands) on three dates, viz., 15 October 2023, 27 October 2023, and 01 December 2023, from an altitude of 40 m and were used to train and test classification models. Classification was performed using six ResNet-50 based hybrid models, namely, ResNet-50+K-Nearest Neighbor (ResNet-50+KNN), ResNet-50+Support Vector Machine (ResNet-50+SVM), ResNet-50+Decision Trees (ResNet-50+DT), ResNet-50+Random Forest (ResNet-50+RF), ResNet-50+Naïve Bayes (ResNet-50+NB), and ResNet-50+Neural Network (ResNet-50+NN), along with two additional DL architectures, namely, You Only Look Once version 5 (YOLOv5) and You Only Look Once version 8 (YOLOv8). Model performance was evaluated using overall accuracy (OA), precision (P), recall (R), kappa coefficient (K), F1-score (F1), and mean Average Precision (mAP). Among the tested classifiers, the ResNet-50+NN model consistently achieved the highest average overall accuracies of 93.16%, 95.81%, and 93.31% at T1, T2, and T3, respectively, outperforming all other models, whose accuracies ranged from 78.05% to 92.07%, 86.11%–95.24%, and 77.47%–92.09% across the respective time intervals. The ResNet-50+NN model also recorded the highest precision (0.93–0.97), recall (0.92–0.97), F1-score (0.92–0.97), and kappa coefficient (0.89–0.96), demonstrating superior and consistent classification performance across all observation dates. The methodology developed in this work enables precise identification of rice establishment methods, improving crop mapping and monitoring. This identification enhances resource efficiency, optimizes input use, and supports site-specific management, contributing to sustainable precision agriculture.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1860176</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1860176</link>
        <title><![CDATA[Hierarchical spectral ensemble with physics-informed augmentation for global water quality retrieval from hyperspectral remote sensing ]]></title>
        <pubdate>2026-09-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Amirthalakshmi TM</author><author>Hemanth S</author><author>Ganesan PV</author><author>Rahul SG</author><author>Gayathri M</author>
        <description><![CDATA[Retrieving water quality variables from remotely sensed reflectance spectra (Rrs) with global-scale, cross-waterbody applicability remains a grand challenge in environmental remote sensing. Here we introduce Hierarchical Spectral Ensemble (HSE), a machine learning pipeline for concurrent retrieval of four ecologically relevant water quality parameters (chlorophyll-a (Chl-a), total suspended solids (TSS), coloured dissolved organic matter absorption coefficient at 440 nm (aCDOM(440)), and Secchi depth (Zsd)), applied to the GLORIA 2022 global dataset of 7,572 co-located hyperspectral in situ ground truth measurements spanning six continents. HSE leverages a combination of five diverse base learners trained with 10-fold out-of-fold stacking, and integrated with a diversity-constrained non-negative least squares (NNLS) meta-learner, supported by a 291-dimensional feature suite spanning spectral, spatial, and temporal representations. We propose Interpolation-based Spectral Data Augmentation (ISDA), an ecologically inspired, class-balance oversampling methodology applied to the training set after the initial stratified split to prevent information leakage. Evaluated on the held-out global test set, HSE attains R2 = 0.822, 0.704, 0.841, and 0.962 for Chl-a, TSS, aCDOM(440), and Zsd respectively (mean R2 = 0.832; all in original physical units following back-transformation). Stratified analysis on a per-quartile basis reveals negative values of R2 in low-concentration regimes for Chl-a, TSS, and aCDOM(440), illustrating how global metrics can mask failures in retrieval across a majority of the distribution, specifically in the oligotrophic regime. This constitutes the primary known limitation of the method: reliable prediction in low-concentration, low-optical-signal regimes remains elusive and is demonstrated only in high-concentration, eutrophic samples where a measurable optical signal exists.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1880618</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1880618</link>
        <title><![CDATA[Simultaneous retrieval of 13 phytoplankton pigments from Sentinel-3 OLCI using convolutional neural networks and transfer learning]]></title>
        <pubdate>2026-09-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Borja Sánchez-López</author><author>Marco Talone</author><author>Jesus Cerquides</author><author>Annalisa Di Cicco</author><author>Gonzalo Martínez-Fornos</author><author>Petra Slavinec</author>
        <description><![CDATA[Phytoplankton pigment concentrations retrieved from ocean color satellite observations provide key information on marine ecosystem composition and biogeochemical cycling. Although Machine Learning (ML) approaches have been applied to multi-spectral sensors such as the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Sea-Viewing Wide Field-of-View Sensor (SeaWiFS), no study has systematically exploited the specific band configuration of the Ocean and Land Colour Instrument (OLCI) onboard Copernicus Sentinel-3 for the simultaneous retrieval of multiple diagnostic pigments. This study presents the first systematic benchmark of five ML architectures: Random Forest (RF), eXtreme Gradient Boosting (XGB), Dense Neural Network (DNN), one-dimensional Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory Network (BiLSTM) for retrieving 13 pigments of interest to the ocean color community from OLCI-equivalent multi-spectral radiometry. Training and evaluation rely on 185 co-located in situ remote-sensing reflectance and High Performance Liquid Chromatography (HPLC) pigment measurements collected across optically diverse European waters (Mediterranean Sea, Black Sea, Atlantic, and English Channel) within the BiOMaP programme. A novel two-phase Deep Learning (DL) training strategy is introduced, in which pigment-specific modules are first trained independently and subsequently concatenated into a joint multi-output model, preventing dominant, easily retrieved pigments from degrading performance for rarer accessory ones. To extend the methodology to operational satellite products, a transfer learning strategy based on fine-tuning is applied and explicitly benchmarked against training from scratch on a global matchup dataset. Additionally, a spectrally reduced version (5 central wavelengths) is developed and validated for compatibility with the Copernicus-GlobColour and European Space Agency’s Ocean Colour Climate Change Initiative datasets, enabling application of the multi-pigment retrieval framework to a 26-year continuous satellite record. Results indicate that CNN consistently outperforms all other architectures across all evaluation metrics, achieving coefficients of determination of 0.70–0.93 and mean absolute percentage errors of 25–55% across the 13 target pigments, close to the approximate 20% average percent differences of published inter-laboratory HPLC measurement round-robin experiments. The fine-tuned model systematically outperforms the from-scratch version across all 13 pigments, with mean absolute percentage errors generally lower than 70% and approximately 20-25% smaller than those obtained when training from scratch, and a coefficient of determination (R2) decreasing by approximately 0.2 relative to the in situ baseline versus a decrease of 0.3 for the from-scratch model. The spectrally reduced model retains comparable in situ performance and similar transfer learning advantages after fine-tuning. These results provide a quantitative demonstration of the value of high-quality regional in situ radiometry as a pre-training foundation for global satellite pigment retrieval. Together, these findings demonstrate the strong potential of OLCI-based CNN models for operational multi-pigment retrieval across current and future satellite missions and for long-term climatological analysis.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1930744</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1930744</link>
        <title><![CDATA[WD-CD: a large-scale high-resolution optical remote sensing benchmark for fine-grained change detection in war scenarios]]></title>
        <pubdate>2026-09-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Dongjing Li</author><author>Lei Ma</author><author>Guangjun He</author><author>Yaohui Chu</author><author>Yingnan Guo</author><author>Ruikun Wang</author><author>Ying Liang</author><author>Pengming Feng</author>
        <description><![CDATA[IntroductionRapid detection of war-induced damage is vital for humanitarian response and post-war reconstruction, yet large-scale, well-annotated benchmarks for war-damage change detection are still lacking.MethodsWe present a large-scale, high-resolution bi-temporal optical remote sensing benchmark for war-damage change detection, named WD-CD. WD-CD contains 9,687 bi-temporal image pairs of 512 × 512 pixels collected from five conflict-affected theaters across Europe, Africa, and Asia, covering a total area of 1,055.83 km2. It provides annotations for 16 target categories and up to six change states. We evaluated representative deep learning models, performed cross-dataset comparisons, and conducted intercontinental transfer experiments.ResultsThe benchmark evaluations demonstrated consistent and competitive performance while revealing the challenges of damage-state discrimination. The intercontinental transfer experiments showed that building geometry generalized well across regions, whereas damage morphology and background landscapes were region-specific.DiscussionWD-CD addresses the lack of large-scale, fine-grained benchmarks for war-damage change detection and provides a foundation for evaluating model performance and cross-regional generalization. To support open science and reproducibility, the dataset will be made available upon request for non-commercial academic research.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1981032</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1981032</link>
        <title><![CDATA[Editorial: Remote sensing applications in mountainous regions]]></title>
        <pubdate>2026-09-09T00:00:00Z</pubdate>
        <category>Editorial</category>
        <author>Divyesh Varade</author><author>Dericks P. Shukla</author><author>Dipankar Mandal</author><author>Narendra Das</author>
        <description></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1838735</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1838735</link>
        <title><![CDATA[Comparative assessment of YOLO-OBB models for AI-enabled mussel raft detection in VHR remote sensing imagery: insights from the Ría de Arousa, Spain]]></title>
        <pubdate>2026-09-04T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Farshid Dabestani</author><author>Armin Moghimi</author><author>Amin Azhir</author><author>Mario Welzel</author><author>Hamid Ebadi</author><author>Mahmod Reza Sahebi</author>
        <description><![CDATA[The rapid expansion of mussel raft aquaculture has increased the demand for accurate and scalable monitoring systems to support sustainable coastal management. Deep learning (DL) object detectors, particularly the YOLO family, enable automated extraction of aquaculture infrastructures from Very High-Resolution (VHR) satellite imagery. However, conventional detectors rely on horizontal bounding boxes that often include excessive background when objects are elongated or rotated, reducing localization accuracy. Oriented bounding box (OBB) detectors address this limitation by modeling object orientation and geometry. In this study, an open-source Python-based graphical user interface (GUI) was developed for automated mussel raft detection, and a comprehensive comparison of YOLOv8-OBB and YOLO11-OBB architectures was conducted using VHR imagery from Spain’s Ría de Arousa. A dedicated mussel raft dataset was compiled and annotated, and both model families were evaluated across five architectural scales (n, s, m, l, and x). Experimental results showed that the YOLO11 family generally outperformed YOLOv8 in terms of detection accuracy, localization quality, and performance under challenging maritime conditions. Among the evaluated models, YOLO11s achieved the highest F1-score (0.866) and mAP50–90 (85.21%), while YOLO11n achieved the highest Mean IoU (0.872) and mAP50 (96.87%). The results further demonstrated that compact architectures can provide a favorable balance between accuracy and computational efficiency, as larger models did not consistently yield superior performance. Large-scale experiments on a 60,309 × 61,569-pixel (50 cm resolution) VHR scene demonstrated the operational scalability of the proposed framework through a patch-based processing strategy. The comparative evaluation conducted in this study provides valuable insights into recent YOLO-OBB architectures and highlights their potential for scalable AI-based aquaculture monitoring.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1914197</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1914197</link>
        <title><![CDATA[Assessing the spatiotemporal dynamics of land-use/land-cover change and human-wildlife conflict around Hluhluwe-iMfolozi park, South Africa]]></title>
        <pubdate>2026-09-03T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ongeziwe Njomi</author><author>Oscar Z. Gwala</author><author>Mohammed B. Altoom</author><author>Abel Ramoelo</author><author>Remi Chandran</author><author>Ram Avtar</author><author>Michael Gebreslasie</author>
        <description><![CDATA[Human‐wildlife conflict (HWC) is increasingly associated with rapid land‐use and land‐cover (LULC) changes and broader environmental shifts. While previous studies have focused on causal factors and coexistence strategies, the spatiotemporal dynamics of human-wildlife interactions under shifting LULC remain poorly quantified. This study examines the spatiotemporal patterns of LULC and their association with HWC around the Hluhluwe‐iMfolozi Park in South Africa. The detailed landscape dynamics were captured using Sentinel‐2 imagery at 5‐year intervals (2015, 2020, and 2025) with machine‐ and deep‐learning classification algorithms. Among the evaluated algorithms, the Two‐dimensional Convolutional Neural Network outperformed the others, achieving an average overall accuracy of 99.92% and a kappa coefficient of 0.9991. The findings show substantial LULC changes during the study, including a notable decrease in cultivated land, changes in vegetation structure, and an increase in built-up areas. Shrubland grew significantly by 2025, suggesting continuous landscape change, while woodland increased between 2015 and 2020. Anthropogenic activities and vegetation gains dominated earlier transitions, while natural vegetation transitions drove later changes. Outside protected regions, these trends were more pronounced, indicating greater anthropogenic pressure. Integration of LULC transitions with HWC data revealed that conflict events were increasingly linked to grassland, woodland, and transitional landscapes and were concentrated along protected area boundaries. Hotspots were closely associated with regions undergoing active land-cover change, and the frequency and spatial extent of HWC increased over time. These results demonstrate how landscape dynamics spatially overlap with human‐wildlife interactions and emphasize the need for sophisticated geospatial technologies to pinpoint conflict hotspots and guide targeted conservation and mitigation efforts.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1915380</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1915380</link>
        <title><![CDATA[Multi-temporal land use/land cover dynamics (2005–2025) and machine learning algorithm comparison in and around kruger national park]]></title>
        <pubdate>2026-08-31T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Oscar Z. Gwala</author><author>Mohammed B. Altoom</author><author>Abel Rameolo</author><author>Michael Gebreslasie</author>
        <description><![CDATA[Land Use/Land Cover (LULC) change detection is fundamental for understanding landscape dynamics and supporting sustainable environmental management, particularly in ecologically sensitive and transboundary conservation areas such as Kruger National Park, South Africa. Rapid urban expansion, agricultural intensification, and environmental change have accelerated landscape transformation, highlighting the need for accurate and reliable LULC monitoring. This study aimed to evaluate long-term LULC dynamics in and around Kruger National Park during 2005, 2015, and 2025 using multi-temporal Landsat imagery and four machine learning classifiers: Random Forest (RF), Support Vector Machine (SVM), Gradient Tree Boosting (GTB), and K-Nearest Neighbors (KNN). In addition, RF-based transition matrices were employed to quantify long-term land cover transformations. The results showed that the Random Forest classifier consistently outperformed the other algorithms, achieving the highest Overall Accuracy (up to 92%) and Kappa coefficient (0.87) across all study years. Gradient Tree Boosting and K-Nearest Neighbors produced satisfactory results, whereas Support Vector Machine exhibited comparatively lower classification performance. Spatial analysis indicated that woodland/shrubland remained the dominant land cover class but experienced progressive fragmentation and conversion to grassland, agricultural land, and bare land. Built- up areas expanded substantially, particularly between 2005 and 2015, while agricultural land also increased, reflecting growing anthropogenic pressure. Water bodies exhibited a declining trend throughout the study period, suggesting increasing hydrological and environmental stress. These findings demonstrate that ensemble-based machine learning methods, particularly Random Forest, provide a robust and reliable approach for monitoring complex and heterogeneous savanna landscapes. The observed LULC changes highlight the increasing influence of human activities on ecosystem structure and emphasize the importance of continuous geospatial monitoring to support biodiversity conservation, sustainable land management, and evidence-based environmental planning. Overall, this study provides a reliable framework for long-term LULC mapping and change detection that can be applied to protected areas and other ecologically sensitive landscapes.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1895172</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1895172</link>
        <title><![CDATA[From foundational models to interpretability: a comparative study of embeddings and feature engineering for smallholder irrigation detection in Sub-Saharan Africa]]></title>
        <pubdate>2026-08-28T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Hasan Siddiqui</author><author>Christopher Small</author><author>Vijay Modi</author>
        <description><![CDATA[Smallholder irrigation is crucial to livelihoods and growth in rural agro-economies. Identifying where it occurs provides valuable insights for agriculture extension, water management, infrastructure investments, marketing and energy provision. Remote sensing methods can aid but have been stymied by the small plot sizes, especially of irrigated plots. Humid tropical climates are characterized by high temperatures and heavy seasonal or year-round rainfall. This adds an additional layer of challenge due to fewer cloud-free imagery from persistent cloud cover. This study focuses on these settings to compare the performance, interpretability and transferability of classification using embeddings versus a feature engineering approach. Geospatial foundation models such as AlphaEarth Foundations (AEF) have emerged to address the contrasting scarcity of high-quality labels in comparison to increasing volumes of earth observation data. The embeddings from these models have been shown to generate maps from sparse labels outperforming traditional machine learning approaches in certain cases. In this study, we utilize a nation-wide smallholder irrigation survey data from Uganda as a data-rich region and pilot surveys from Zambia as a data-sparse region. We present a reproducible cloud-native Earth observation workflow in Google Earth Engine that discusses the tradeoffs and performance of the feature engineering approach compared to foundational model embeddings. The results show that a model trained on AEF embeddings outperforms a traditional feature engineering approach on a rich label dataset. The performance is similar in a data-sparse region. However, the embedding models do not lend themselves to auditable methods for applicability to regions where no data is available.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1863721</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1863721</link>
        <title><![CDATA[Assessing temporal sampling uncertainty in hydrological modelling using multi-sensor observations from GPM and TROPICS]]></title>
        <pubdate>2026-08-28T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ajay Sharma</author><author>Dibyandu Roy</author><author>Indu J</author>
        <description><![CDATA[Satellite-based precipitation products are widely used for hydrological modelling; however, temporal sampling uncertainty caused by infrequent satellite overpasses can significantly affect runoff estimation, particularly in mountainous and flood-prone watersheds. This study evaluates the influence of temporal sampling uncertainty in precipitation on runoff simulation using multi-sensor combination data from two different satellite constellations (Global Precipitation Measuring Mission-GPM and Time Resolved Observations of Precipitation Structure and Storm Intensity with a Constellation of Smallsats - TROPICS) constellations over the Ranikhola watershed in the eastern Himalayas, India. Five GPM sensors (GMI, SSMIS, MHS, AMSR2, and ATMS) and three TROPICS CubeSats (T3, T5, and T6) were analysed individually and in different combinations. Sensor overpass times were collocated with IMERG precipitation data, and the derived rainfall was used to simulate runoff in the HYSIM (lumped model) hydrological model during 2016–2020. Results show that increasing the number of sensors improved sampling frequency, reduced revisit gaps, and enhanced runoff simulation accuracy. The combined TROPICS configuration (T3–T5–T6) achieved the best performance, with NSE = 0.6983, R2 = 0.9568, RMSE = 7.75 m3 s−1, and MAE = 5.62 m s−1, whereas the GMI–SSMIS combination showed poor performance with NSE = −1.7385 and RMSE = 23.36 m3 s−1. The TROPICS constellation provided more than 12 overpasses per day, compared to ∼1–2.5 overpasses per day for individual GPM sensors. The findings demonstrate that high-frequency CubeSat constellations substantially reduce temporal sampling uncertainty and improve runoff estimation, highlighting their potential for flood forecasting and hydrological applications in data-scarce mountainous regions.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1894138</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1894138</link>
        <title><![CDATA[Analysis of atmospheric air pollutants (CO, NO2, and SO2), through Sentinel-5P images in google earth engine, apurimac region, period 2020–2023]]></title>
        <pubdate>2026-08-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Walquer Huacani Calsin</author><author>Hernán Yari</author><author>Edgar Vilca</author><author>German Espinoza</author><author>Franklin Lozano</author>
        <description><![CDATA[Atmospheric pollution associated with carbon monoxide (CO), nitrogen dioxide (NO2), and sulfur dioxide (SO2) represents an important environmental and public health concern in Andean regions influenced by urban growth, transportation, agricultural burning, mining-related activities, and complex topography. This study analyzed the spatiotemporal variability of CO, NO2, and SO2 in the Apurimac region, Peru, during 2020–2023 using Sentinel-5P/TROPOMI satellite products processed in Google Earth Engine. The original column-density data, expressed in mol/m2, were converted into column-derived estimated concentrations using a simplified effective lower-atmospheric layer height of 2,000 m. These values were used only as relative indicators and were not interpreted as direct ground-level air quality measurements. The results showed heterogeneous spatial patterns across Apurimac. CO presented relatively higher values mainly in Abancay, Chincheros, and Andahuaylas, while NO2 showed higher relative values in Cotabambas, Grau, Abancay, and Chincheros. SO2 exhibited a more irregular and uncertain behavior, with localized positive values, negative retrievals, and high variability, indicating greater sensitivity to satellite retrieval noise. Therefore, SO2 was interpreted as an exploratory indicator rather than robust evidence of province-level pollution hotspots. Temporal analysis showed seasonal fluctuations and isolated peaks, especially during dry-season months. Trend detection was performed using the Mann-Kendall test and Sen’s slope estimator. CO showed a statistically significant decreasing trend, NO2 showed a weak but statistically significant increasing trend, and SO2 did not show a statistically significant trend. Overall, Sentinel-5P/TROPOMI and Google Earth Engine proved useful for identifying relative pollutant patterns in a data-sparse Andean region. Future studies should integrate satellite observations with in situ measurements, meteorological data, boundary-layer information, emission inventories, and independent datasets to improve validation, source attribution, and regional air quality assessment.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1863355</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1863355</link>
        <title><![CDATA[GF-2/sentinel-2 fusion for active fault detection: a case study of the yilan-yitong fault (liaoning segment)]]></title>
        <pubdate>2026-08-19T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Chang Cao</author><author>Xiaodong Jia</author><author>Chao Wang</author><author>Bo Wan</author><author>Chenyang Gao</author><author>Meng Yuan</author><author>Yiyue Wang</author>
        <description><![CDATA[The Yilan-Yitong Fault Zone, a core part of the northern Tanlu Fault Zone, is a key seismogenic structure in Northeast Asia. Its Liaoning segment suffers from unclear surface distribution, insufficient late Quaternary activity evidence and lack of refined research based on optimized multi-source remote sensing data, which restricts regional seismic hazard assessment and major engineering safety layout. This study aimed to conduct fine detection and activity evaluation of this fault segment using high-resolution satellite data. We took GF-2 panchromatic and Sentinel-2 multispectral images as core data, compared four fusion algorithms (PCA, GS, HSV, Brovey) via qualitative and quantitative evaluation, and combined UAV remote sensing, field surveys of 28 key observation points and large-scale trench (25 m × 8 m) verification in Kaiyuan for systematic analysis. Results showed the PCA algorithm had the optimal comprehensive performance, suitable for fine geological interpretation. The fault was divided into three subsegments, with the Tieling-Kaiyuan segment showing distinct linear geomorphology and strong late Quaternary activity. The trench provides evidence suggestive of Holocene activity, and flower structures plus multi-phase faulting events reflected multistage activity characteristics, with preliminary identification of paleoseismic relics. This study verifies the application potential of domestic high-resolution satellites, fills the gap in refined activity research of the fault’s Liaoning segment, and provides high-precision scientific support for Liaoning’s seismic hazard assessment and major engineering safety layout.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1867220</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1867220</link>
        <title><![CDATA[Assessment of land suitability for agriculture production using hybrid approaches: trapezoidal fuzzy number analytic hierarchy process, remote sensing and GIS]]></title>
        <pubdate>2026-08-19T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Prabu Babu</author><author>Saurabh Chandra Maury</author>
        <description><![CDATA[IntroductionLand suitability assessment is crucial for identifying areas with high potential for agricultural production, promoting sustainable land use, and addressing food security challenges. In the study area, approximately 70% of the population depends on agriculture for their livelihood. Therefore, assessing land suitability is essential for ensuring efficient land utilization and enhancing agricultural productivity. Consequently, Dharmapuri District, Tamil Nadu, India, was selected as the study area. To evaluate agriculture production, several key parameters were analyzed, including Land Use and Land Cover (LULC), Slope (S), Depth to water level (DL), Soil Texture (ST), Annual Rainfall (AR), pH, Nitrogen (N), Organic Carbon (OC),Temperature (T), Soil Moisture (SM), Distance to River (DR), Aspect (A), Elevation (E), Proximity to road (PRD), Normalized Difference Built up Index (NDBI) and Salinity (S). The selected parameters were chosen based on their proven relevance in previous land suitability assessment studies. The study aims to evaluate Land Suitability Zone (LSZ) using hybrid approaches Trapezoidal Fuzzy Numbers Analytic Hierarchy Process (TRFN‐AHP), remote sensing and Geographic Information System (GIS).MethodsThe parameter weights were calculated using the TRFN‐AHP method.Result and DiscussionBased on the results, the land suitability for agriculture production was classified as not suitable (8.86%), marginally suitable (20.70%), moderately suitable (24.88%), highly suitable (27.12%) and very highly suitable (18.44%). The results of land suitability index for agriculture production was validated using Receiver Operating Characteristic (ROC) curve. In ROC curve, the area under the curve value is 0.76 indicates good predictive accuracy in the study area. Overall, the results demonstrate that the hybrid approach combining TRFN‐AHP, remote sensing, and Geographic Information System provides an effective decision-support framework for assessing land suitability for agricultural production, facilitating sustainable land‐use planning and improved agricultural productivity.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1843759</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1843759</link>
        <title><![CDATA[Testing a computed tomography imaging spectrometer for Earth observations on the HEIMDAL stratospheric balloon mission]]></title>
        <pubdate>2026-08-13T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Mads Juul Ahlebæk</author><author>Albertino Antonio Almeida Bach</author><author>Loui Collin-Enoch</author><author>Christian Cordes</author><author>Boas Hermansson</author><author>Christian Hald Jessen</author><author>Søren Peter Jørgensen</author><author>Tobias Jørgensen</author><author>Viktor Ulrich Kanstrup</author><author>Laurits Tværmose Nielsen</author><author>Jes Enok Steinmüller</author><author>Mads Svanborg Peters</author><author>Jonathan Merrison</author><author>René Lynge Eriksen</author><author>Christoffer Karoff</author><author>Mads Toudal Frandsen</author>
        <description><![CDATA[Stratospheric high-altitude balloons (HABs) have great potential as remote sensing platforms for Earth observations, complementing orbiting satellites and low-flying drones. At altitudes of 20–35 km, HABs operate significantly closer to the ground than orbiting satellites but significantly higher than most drones. Therefore, HABs offer unique potential for high-spatial-resolution imaging with large-area coverage. Two other imaging parameters important for Earth observation applications are spectral resolution and spectral range. Hence, in this work, we present the development and testing of a hyperspectral imaging system capable of recording near-video-rate images in narrow contiguous spectral bands from a HAB platform. In particular, we present the first stratospheric environmental tests and HAB flight of a snapshot hyperspectral camera based on computed tomography imaging spectroscopy, which is well-suited to address the challenges posed by the motion of the HAB platform and stratospheric environment. We successfully acquired images with the system under both simulated stratospheric conditions in the Mars Simulation Laboratory at Aarhus University and a 5-h HAB flight mission named HEIMDAL from Kiruna in October 2024 as part of the REXUS/BEXUS 34/35 2024 campaign organized by DLR-SNSA. This study represents a step toward deploying the HAB platform for high-quality land-cover classification.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1803946</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1803946</link>
        <title><![CDATA[Integrated eco-environmental risk mapping in the mountainous tropical landscapes of the Western Ghats, Kerala]]></title>
        <pubdate>2026-08-13T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>J. Drisiya</author><author>Sarmistha Singh</author>
        <description><![CDATA[Rapid tourism expansion and infrastructure growth in the Western Ghats are reshaping ecological stability in steep, topographically complex landscapes that still retain substantial forest cover. These changes are intensifying habitat fragmentation, degrading ecosystems, and placing increasing pressure on biodiversity-rich environments. Focusing on Idukki district in southern India, this study integrates the Urban Nature Access (UNA) and Habitat Risk Assessment (HRA) modules within the InVEST framework to quantify how accessibility-driven development influences habitat vulnerability between 2011 and 2025. Results reveal a widening spatial imbalance between population demand and accessible natural areas, with strongly negative urban nature balance values expanding across valley settlements and plantation corridors by 2025. Built-up land exhibits the highest mean habitat risk (R̄ = 0.42), followed by plantations (R̄ = 0.38) and croplands (R̄ = 0.34), while deciduous forests (R̄ = 0.22) and water bodies (R̄ = 0.05) remain comparatively less vulnerable. More than one-third of built-up and plantation landscapes fall within medium to high-risk categories. Spatial overlap between high-risk zones and documented landslide-affected areas during the 2018–2020 extreme monsoon events highlight the cumulative impact of tourism-driven development and associated forest conversion on steep slopes. The findings demonstrate that ecological vulnerability in Idukki is closely linked to localized forest loss and land-use transformation driven by concentrated human activities in hazard-prone terrain. These patterns highlight how steep and environmentally sensitive landscapes are increasingly affected by development pressures. This underscores the need to integrate ecosystem accessibility metrics with slope-sensitive land-use planning in tropical mountain systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1931285</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1931285</link>
        <title><![CDATA[Editorial: Rising stars in remote sensing 2025: advancements in time series analysis]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Editorial</category>
        <author>Jane Southworth</author><author>Nicolas Baghdadi</author>
        <description></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1843209</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1843209</link>
        <title><![CDATA[AI-driven prediction of plant physiological traits in hemp using UAV-based multispectral imagery]]></title>
        <pubdate>2026-08-04T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Harjot Sidhu</author><author>Arnab Bhowmik</author><author>Harmandeep Sharma</author>
        <description><![CDATA[IntroductionIndustrial hemp (Cannabis sativa L.) is a multipurpose bio‐economy crop capable of producing fiber, grain, and biomass while contributing to soil health and carbon sequestration. Realizing this potential requires optimized nitrogen (N) management, as N strongly regulates plant growth, yield, and fiber quality, while inefficient or excessive N use can cause environmental harm. Conventional N diagnostics based on destructive sampling are labor‐intensive and lack the spatial resolution needed for precision management. Uncrewed aerial vehicle (UAV) multispectral imaging offers a high-throughput, non‐destructive alternative; however, hemp remains underrepresented in UAV‐based N studies, particularly in linking spectral data to physiological traits associated with N metabolism.MethodsTo address this gap, two field experiments were conducted at the North Carolina A&T State University research farm using dual‐purpose and fiber‐type hemp cultivars under contrasting N regimes during the 2024 and 2025 growing seasons. Multispectral imagery was collected using a WingtraOne GEN II UAV equipped with a MicaSense RedEdge‐P camera. From reflectance mosaics, 33 vegetation indices (VIs) were computed, and the top seven were selected using Spearman's correlation analysis. Ground measurements included SPAD chlorophyll readings and gas‐exchange traits, i.e., net photosynthetic rate (Pn), stomatal conductance (Gs), and transpiration rate (E), using a LI‐COR 6800 system. Using SAS Viya, multiple supervised learning models were developed to predict SPAD, Pn, Gs, and E from UAV‐derived VIs.ResultsRed‐edge and green‐based indices showed very strong correlations with SPAD (ρ = 0.9078−0.9375), while NDWI showed a strong negative relationship (ρ = −0.9623). For Pn, GNDVI and CIG were strongly correlated (ρ ≈ 0.89), with NDWI negatively associated (ρ = −0.8934). Gs and E exhibited moderate correlations (ρ ≈ 0.73−0.84 and 0.75−0.80). Linear regression achieved R2 = 0.88 for SPAD, while a generalized additive model predicted Pn with R2 = 0.87. Quantile regression performed best for Gs and E (R2 = 0.82 and 0.75; Gs: ASE ≈0.013, MAE ≈0.086; E: ASE ≈0.0003, MAE ≈0.014).DiscussionThese results demonstrate a scalable framework for UAV‐based phenotyping to support precision N management in hemp.]]></description>
      </item>
      </channel>
    </rss>