<?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>2026-07-29T12:27:33.62+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1931394</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1931394</link>
        <title><![CDATA[Editorial: Machine learning for advanced remote sensing: from theory to applications and societal impact]]></title>
        <pubdate>2026-07-24T00:00:00Z</pubdate>
        <category>Editorial</category>
        <author>Rui Li</author><author>Shaoqing Dai</author><author>Bin Jiang</author><author>Cong Zhang</author><author>Haoyang Yang</author><author>Wufan Zhao</author>
        <description></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1856867</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1856867</link>
        <title><![CDATA[Comparative analysis on spectral characteristics of PRISMA and EnMAP hyperspectral missions]]></title>
        <pubdate>2026-07-24T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Valeria La Pegna</author><author>Sora Seo</author><author>Davide De Santis</author><author>Fabio Del Frate</author><author>Diego Loyola</author>
        <description><![CDATA[Given the similarities in their instrumental characteristics, a comparative analysis was conducted between hyperspectral missions of PRISMA, operated by the Italian Space Agency (ASI), and EnMAP, developed by the German Aerospace Center (DLR). This work investigates both the similarities and discrepancies between these two satellite optical data, providing an outline of the spectral regions where data from both sensors can be reliably interchanged. The analysis was performed by analyzing the full visible and near-infrared (VNIR) spectrum and by examining selected spectral ranges sensitive to key environmental parameters, such as nitrogen dioxide, chlorophyll and NDVI. A total of 11 PRISMA and EnMAP co-located hyperspectral image pairs acquired across different seasons over the Euro-Mediterranean region were analyzed, focusing on representative land cover classes (bare soil, vegetation, urban areas and waters). Preprocessing steps were applied to standardize the acquisition viewing geometries, and the top of atmosphere (TOA) level of products from the two sensors were used to avoid inconsistencies introduced by atmospheric correction schemes adopted by each operating agency. Overall, the quantitative and qualitative assessments confirm a strong correspondence between the PRISMA and EnMAP hyperspectral measurements across the VNIR spectrum, with SAM always below 0.1 rad. However, the statistical analysis reveals relatively low consistency between the two sensors for the vegetation sensitive spectral window (750–940 nm), where larger deviations are observed with STD of 0.067 and SAM of 0.097, while the NO2 spectral range (420–500 nm) shows lower SAM of 0.048 and STD of 0.045.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1877406</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1877406</link>
        <title><![CDATA[Estimating forest aboveground carbon stock from remote sensing data with an enhanced XGBoost model]]></title>
        <pubdate>2026-07-23T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Chenfei Shi</author><author>Cui Jia</author><author>Linghan Gao</author><author>Qi Liu</author><author>Haonan Wang</author><author>Mengyu Xu</author>
        <description><![CDATA[The accurate assessment of forest aboveground carbon (AGC) is crucial for improving the efficiency of forest resource management, mitigating climate change, and fostering sustainable development. However, the extensive distribution of forests, their complex ecosystem structures, insufficiently representative assessment data, and methodological inconsistencies generally lead to estimates with low accuracy and high uncertainty. To address these issues systematically, this study introduces a novel framework that integrates remote sensing features with field-measured plot data. This framework leverages an Optuna-optimized eXtreme Gradient Boosting (XGBoost) model to achieve accurate estimation of forest AGC. A key contribution of this study is the application of Optuna to optimize the hyperparameters of the XGBoost model, which improves both its predictive performance and generalization ability. For feature selection, we employed a combination of the Pearson correlation coefficient and the Boruta algorithm, which identified ten core feature variables from the initial set. This process effectively improved the relevance and interpretability of the model inputs. The experimental results demonstrate that feature selection markedly improved model performance: R2 increased by 0.2, RMSE decreased by 2.33 Mg C/ha, and MAE was reduced by 6.21% compared to the model using the unselected feature set. The Optuna-optimized XGBoost model demonstrated excellent performance, achieving an R2 of 0.72, an improvement of 0.12 over the baseline XGBoost model, with an RMSE of 24.48 Mg C/ha and an MAE of 18.56%. These results indicate superior predictive accuracy and stability. In conclusion, the integrated framework developed in this study, which combines multi-source remote sensing data with machine learning, effectively enhances the estimation accuracy of forest AGC at a regional scale. This approach provides a reliable theoretical basis and a practical methodology for the dynamic monitoring and management of forest carbon sinks.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1861186</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1861186</link>
        <title><![CDATA[High-precision individual tree canopy segmentation from UAV remote sensing imagery based on the improved BKFE-UNet model]]></title>
        <pubdate>2026-07-22T00:00:00Z</pubdate>
        <category>Methods</category>
        <author>Qi Liu</author><author>Cui Jia</author><author>Linghan Gao</author><author>Haonan Wang</author><author>Chenfei Shi</author><author>Mengyu Xu</author><author>Kaiyu Jia</author><author>Siyu Ma</author>
        <description><![CDATA[Canopy segmentation is a crucial step in obtaining canopy parameters in forestry remote sensing, and it holds significant importance for research areas such as forest carbon sequestration. However, canopy segmentation based on UAV imagery still faces challenges including confusion between edges and background, as well as insufficient edge details. To address these issues, this paper proposes a semantic segmentation network based on U-Net which implements boundary and key feature enhancement named BKFE-UNet, which is built upon the U-Net model and integrates a differential boundary attention module (DBM) and a key feature enhancement module (KFEM). The DBM enhances canopy edge information through differential computation, alleviating problems such as adhesion between adjacent canopy edges and inadequate edge details. The KFEM introduces Ghost convolution; by stacking Ghost features, it simultaneously filters out redundant information and enhances the key semantic features of canopy objects, thereby reducing background interference. On the UAV tree canopy segmentation dataset, BKFE-UNet achieves an mPA of 92.62%, an mIoU of 86.50%, an Accuracy of 96.30%, and an F1-score of 0.90, representing improvements of 2.23%, 2.27%, 2.09%, and 0.02, respectively, over the baseline U-Net, demonstrating a significant improvement over the baseline U-Net model.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1827393</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1827393</link>
        <title><![CDATA[A multi-class, multi-temporal crop and Land cover mapping framework for Morocco using Sentinel-1/2 monthly composites and advanced machine learning ensembles]]></title>
        <pubdate>2026-07-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Maryam Choukri</author><author>Yacine Bouroubi</author><author>Jamal-Eddine Ouzemou</author><author>Said Grich</author><author>Guy Armel Kamga Fotso</author><author>Saeid Ojaghi</author><author>Abdelghani Chehbouni</author><author>Ahmed Laamrani</author>
        <description><![CDATA[Timely and accurate crop-type mapping is fundamental for sustainable agricultural management and food security in semi-arid regions, where climate variability and fragmented landscapes present persistent challenges. This study develops and validates an operational, multi-temporal framework for classifying five key agricultural classes (i.e., soft wheat, durum wheat, barley, trees, and other crops) across diverse Moroccan agroecosystems. By integrating monthly Sentinel-1 Synthetic Aperture Radar and Sentinel-2 optical time series spanning six growing seasons (2018–2025), we extracted 156 features comprising 13 spectral indices across 12 monthly composites. Ground truth data from the national Al Moutmir database, strategically balanced to address natural class imbalances, supported comprehensive training and validation of six machine learning models (i.e., Random Forest, Extra Trees, XGBoost, LightGBM, Voting Ensemble, and Stacking Ensemble). Our findings showed that the LightGBM and Stacking Ensemble achieved the highest performance with 88.04% overall accuracy, followed closely by XGBoost (87.93%). Feature importance analysis revealed that monthly temporal resolution significantly outperformed traditional phenological-stage approaches, with March and April indices (particularly Normalized Difference Vegetation Index and Normalized Difference Red Edge) contributing most to class discrimination. Notably, early-season radar features (Vertical-Vertical polarization in September) provided valuable complementary information when optical data were limited. The framework demonstrated robust generalization through 10-fold cross-validation while explicitly quantifying a 12.56% overfitting gap (train-CV difference), acknowledging a non-negligible overfitting risk. Offering transparent performance assessment. Error analysis identified persistent confusion between spectrally similar cereals, particularly durum and soft wheat, highlighting priority areas for future sensor integration. This scalable, cloud-based pipeline directly supports Morocco’s Green Generation strategy by providing a reproducible, high-accuracy solution for annual crop inventories, with transferable applications across similar Mediterranean and semi-arid agricultural systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1793996</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1793996</link>
        <title><![CDATA[Intra-event extreme rainfall characterization in the tropical Andes: a high-resolution weather radar approach]]></title>
        <pubdate>2026-07-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Gabriela Urgilés</author><author>Rolando Célleri</author><author>Daniela Ballari</author><author>Jörg Bendix</author><author>Johanna Orellana-Alvear</author>
        <description><![CDATA[IntroductionHydrological hazards, such as floods and landslides are frequently driven by extreme rainfall events (ERE). Thus, understanding the spatio-temporal patterns and intra-event behavior of these events is important for identifying vulnerable regions, improving early warning systems, and enhancing water management.MethodsThis study aimed to analyze the spatio-temporal intra-event characteristics of ERE, using high-resolution (5min) weather radar data focusing on their internal structure and spatial distribution. The study was conducted in the headwaters of the Paute basin (2,200–4,400 m a.s.l.) in southern Ecuador. Based on three ERE classes, four intra-event rainfall features were analyzed: area, maximum rainfall, cohesion, and the locations of rainfall hotspots.ResultsThese features revealed different rainfall patterns for the three distinct rainfall classes. Class 1 is characterized by the highest rainfall peaks, concentrated between 12:00 and 19:00 (afternoon). Class 3 shows the lowest rainfall peaks. Class 2 shows the least cohesive rainfall core and a mixed behavior in features. Regarding the locations of rainfall hotspots, classes 1 and 2 show hotspots located at the catchment outlets and at the urban (City of Cuenca) areas of the sub-catchments (around 2,500 m a.s.l), while those in class 3 are found at headwaters (above 3,500 m a.s.l).DiscussionIdentifying these rainfall characteristics and hotspot location provides a better understanding of extreme rainfall behavior in the tropical Andes, which enhances knowledge of hydrological processes, and improves flood forecasting.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1825086</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1825086</link>
        <title><![CDATA[Global assessment of merged multi-sensor ocean-colour chlorophyll-a products]]></title>
        <pubdate>2026-07-21T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Silvia Pardo</author><author>Gavin H. Tilstone</author><author>Giorgio Dall’Olmo</author><author>Thomas M. Jordan</author><author>Robert J. W. Brewin</author><author>Tania G. D. Casal</author>
        <description><![CDATA[Chlorophyll-a concentration (chl-a) is important to assess the health and state of ocean ecosystems. With the availability of global ocean-colour chl-a estimates that now span 25 years, there has been a concerted effort to produce merged data products from different satellite sensors to assess changes in chl-a over the global ocean for long periods of time. However, to date, the performance of these merged chl-a products has not been thoroughly assessed. To perform such an assessment, we assembled a large global in situ dataset of quasi-autonomous spectrophotometrically-derived chl-a that resulted in >13,000 satellite match- ups and then filtered them to produce the highest quality data. The suite of merged ocean-colour chl-a products assessed using the in situ chl-a included two Ocean Colour - Climate Change Initiative (OC-CCI) versions (OC-CCI v5 and OC-CCI v6), two GlobColour products and the Copernicus Marine Environment Monitoring Service (CMEMS) GlobColour L3 and L4 and CMEMS-CCI products. The results confirm that spectrophotometrically-derived chl-a estimates can achieve considerably larger numbers of satellite match ups and lower root mean squared errors in validation than those obtained from discrete estimates of chl-a. Using these data, all of the satellite products (except the GlobColour L4 gap-filled one) exhibited similarly consistent results with the in situ chl-a data with a mean relative percentage difference of 30%. Residuals (differences between in situ and satellite product data) were not homogeneously distributed across chl-a ranges however, with mainly negative residuals at low and high chl-a and mainly positive residuals at intermediate chl-a. These results illustrate that absolute biases of the order of 20%–50% still affect these merged products in specific parts of the chl-a range.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1890112</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1890112</link>
        <title><![CDATA[Evaluating statistical downscaling methods for future temperature and precipitation projections in the Qilian mountains]]></title>
        <pubdate>2026-07-17T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Guohua Liu</author><author>Chanchan Gao</author><author>Zhangwen Liu</author><author>Huibang Han</author><author>Chuntan Han</author><author>Jiaze Li</author><author>Rensheng Chen</author>
        <description><![CDATA[The Qilian Mountains, a crucial ecological security barrier and water conservation region in northwestern China, are highly sensitive to climate change. Reliable climate projections are essential for regional environmental management, yet the performance of statistical downscaling methods in this complex mountainous region remains inadequately evaluated. This study evaluates four statistical downscaling methods—Delta Change Method (DCM), Quantile Mapping (QM), Multiple Linear Regression (MLR), and Random Forest (RF)—using station-based observations (1951–2025) and outputs from 34 CMIP6 climate models. Validation results indicate that RF achieved the highest R2 and the lowest RMSE for both temperature and precipitation, with superior stability across models, scenarios, and stations. Based on RF downscaling, future climate projections under SSP1–2.6, SSP2–4.5, SSP3–7.0, and SSP5–8.5 indicate a persistent warming and moderate wetting trend throughout the 21st century. Temperature is projected to increase at rates of 0.03 °C–0.31 °C/decade, while precipitation is projected to increase by approximately 3.2%–8.1% by the end of the century, although inter-model uncertainty remains substantial. Future climate change also exhibits pronounced seasonal and spatial heterogeneity, characterized by winter-dominated warming, reduced summer precipitation but increased autumn–winter precipitation, and strong elevation-dependent responses concentrated in high-elevation areas. The 0 °C isotherm is projected to rise by approximately 100–400 m by the late 21st century. These findings highlight the applicability of RF downscaling for station-scale climate projections in the Qilian Mountains and provide scientific support for regional climate adaptation, water resource management, and ecosystem conservation.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1813566</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1813566</link>
        <title><![CDATA[Integration of radiative transfer–machine learning for physiological mapping of leaf chlorophyll and anthocyanin in cotton]]></title>
        <pubdate>2026-07-08T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Prachi Singh</author><author>Mohan K. Bista</author><author>Chamika A. Silva</author><author>Nuwan K. Wijewardane</author><author>John P. Brooks</author><author>Prakash Kumar Jha</author><author>Raju Bheemanahalli</author>
        <description><![CDATA[Accurate, non-invasive measurements of leaf biophysical parameters are crucial for assessing crop health and advancing precision agriculture. This study combined an uncrewed aerial system (UAS) drone with radiative transfer modeling and machine learning techniques to estimate two key cotton traits: Leaf Chlorophyll Content (LCC) and Anthocyanin (Anth). Ground-based leaf hyperspectral data collected with a PSR + Spectroradiometer and handheld multi-pigment to match the drone data and support validation. The PROSPECT-D model for leaf optical properties was utilized within the Automated Radiative Transfer Models Operator (ARTMO) framework to conduct forward simulations. Concurrently, inverse modeling was executed using the Machine Learning Regression Algorithms (MLRA) toolbox. During the calibration phase (70% of the dataset) and the validation phase (30% of the dataset), six machine learning algorithms were assessed under various spectral and parameter noise conditions. Among these, Gaussian kernel regression demonstrated the better relative performance, achieving correlation coefficients (r) of 0.82 and 0.78 for LCC and Anth, respectively. The parameter mapping derived from UAS data revealed spatial variability in LCC (0.2–0.6) and in Anth (0.01–0.09) across the study field. Validation results showed strong correlations with ground-truth data, with r values of 0.74 and 0.71 for LCC and Anth, respectively. These findings highlight the potential to integrate UAS data, radiative transfer models, and machine learning to non-invasively estimate crop biophysical parameters and spatially monitor crop physiological variability, thereby facilitating effective precision agriculture practices.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1882437</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1882437</link>
        <title><![CDATA[Neutrosophic soft-computing ensemble for high-accuracy satellite image scene classification]]></title>
        <pubdate>2026-07-08T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ezhilmaran Devarasan</author><author>Maxime Mahieu Josse</author><author>Sm Arun</author><author>V. Vishal</author><author>Bapathu Koushika</author><author>Abhyuday Singh</author><author>Jenisha Rachel</author>
        <description><![CDATA[Satellite image scene classification is a fundamental task in remote sensing. It underpins land-use monitoring, urban planning, disaster response, and environmental management. Despite substantial progress through deep learning, complex aerial scenes remain challenging owing to high inter-class visual similarity, intra-class spatial variance, and inherent prediction uncertainty across heterogeneous model architectures. This paper proposes a novel triple-branch ensemble framework that combines three architecturally complementary deep learning backbones-ConvNeXt-Small, HRNet-W18, and Swin Transformer (Small) - to jointly exploit local texture hierarchies, high-resolution spatial representations, and global self-attention context. To advance beyond conventional probability averaging, three uncertainty-aware soft-computing fusion strategies are developed and compared: Normal Fuzzy logic, Intuitionistic Fuzzy logic, and Neutrosophic logic. The proposed Neutrosophic fusion decomposes each branch output into Truth, Indeterminacy, and Falsity components, explicitly down-weighting predictions characterised by high inter-branch disagreement. Experiments are conducted on the UC Merced Land Use Dataset (21 classes, 2,100 images) using a stratified 80/20 split with a comprehensive eight-stage preprocessing pipeline and ImageNet transfer learning. The proposed Neutrosophic Ensemble achieves 99.29% accuracy and the highest precision of 99.31%, outperforming all individual backbones and simpler ensemble baselines. These results suggest that architectural complementarity combined with neutrosophic uncertainty modelling is a promising approach for satellite image scene classification on this benchmark, though validation on larger and more diverse datasets remains an important next step.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1804569</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1804569</link>
        <title><![CDATA[Explainable HybridEnsemble approach with golden jackal optimization for AGB estimation using multi-sensor remote sensing]]></title>
        <pubdate>2026-07-07T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Abraham Aidoo Borsah</author><author>Man Sing Wong</author><author>Majid Nazeer</author><author>Shao-Yuan Leu</author><author>Jin Wu</author><author>Amos P. K. Tai</author><author>Janet Elizabeth Nichol</author>
        <description><![CDATA[Accurate spatial measurement of aboveground biomass (AGB) is essential for assessing carbon stocks in the forest ecosystem. To enhance this estimation, integrating active and passive Earth Observation data with advanced machine learning techniques offers a promising approach. This study presents an integrated HybridEnsemble model with golden jackal optimization for AGB estimation and evaluates its predictive performance against individual base-learners, including categorical boosting (CatBoost), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and adaptive boosting (AdaBoost) via the synergistic application of Explainable Artificial Intelligence (XAI) and active and passive datasets. The findings revealed a clear performance ranking among these models, with the HybridEnsemble Golden Jackal Optimization (HGJO) model identified as the most effective, which yielded a correlation coefficient (R2) of 0.821 and a Relative Root Mean Square Error (rRMSE) of 16.30%. This performance was followed by CatBoost (R2 = 0.816, rRMSE = 16.51%), LightGBM (R2 = 0.804, rRMSE = 17.05%), XGBoost (R2 = 0.802, rRMSE = 17.13%), and AdaBoost (R2 = 0.731, rRMSE = 19.97%), with all comparisons reported at 95% confidence intervals. XAI revealed that predictors from optical sensors (passive) were strongly correlated with AGB and played a significant role in predicting AGB, while features derived from SAR (synthetic aperture radar, an active sensor), less influential, provided unique backscatter and context-specific insights that enhanced the model’s performance. Forecast results indicate an increasing trend. Additionally, the analysis revealed that future AGB accumulation in the subtropical forest of Hong Kong will be highly variable and strongly dependent on initial biomass levels, with high-biomass plots likely to see the greatest gains. However, spatial uncertainty in AGB predictions varied across the study area, with higher uncertainties observed in forested areas and lower uncertainties in urban areas. Overall, this study not only enhances understanding of optimized hybrid ensemble models for biomass prediction but also offers valuable insights for forecasting forest dynamics, supporting sustainable forest management and carbon stock monitoring globally.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1877713</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1877713</link>
        <title><![CDATA[Sequential feature selection for efficient landslide segmentation from multi-spectral data]]></title>
        <pubdate>2026-07-07T00:00:00Z</pubdate>
        <category>Brief Research Report</category>
        <author>Arsalaan Ahmad</author><author>Oktay Karakuş</author><author>Paul L. Rosin</author>
        <description><![CDATA[Landslide detection from satellite imagery has advanced through deep learning, yet most models rely on large, highly correlated spectral-topographic inputs whose contributions remain poorly understood. The question of which channels are actually necessary has received surprisingly little attention. This matters: redundant or correlated inputs obscure physical interpretability, inflate computational overhead, and can actively degrade model performance through the Hughes Phenomenon. We present a systematic, explainable channel-selection framework for the Landslide4Sense benchmark, combining Sentinel-2 multispectral and ALOS PALSAR terrain data with 16 engineered spectral and structural indices. Rather than relying on conventional single-band drop tests, which evaluate channels in isolation and miss interaction effects, we apply Sequential Forward Floating Selection (SFFS) to iteratively build and prune a candidate feature pool using a lightweight U-Net++ proxy model. Beyond identifying a compact 8-channel subset that matches or exceeds the segmentation F1 of configurations using up to 30 channels, we use the selection process itself to interrogate which spectral and topographic features landslide models genuinely rely on, and what this reveals about the physical cues driving their predictions. We argue that SFFS represents a principled feature selection approach to input design in Earth observation, in contrast to the prevailing practice of appending every available band and hoping the model learns what to ignore.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1843303</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1843303</link>
        <title><![CDATA[Application of the Radon transform to multi-angle measurements made by the research scanning polarimeter: a new approach to cloud tomography, Part III—accuracy and applicability]]></title>
        <pubdate>2026-07-03T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Mikhail D. Alexandrov</author><author>Bastiaan van Diedenhoven</author><author>Brian Cairns</author>
        <description><![CDATA[In Part III of the series, we evaluate the accuracy and applicability of the tomographic algorithm introduced in Part I and applied to real measurements by the research scanning polarimeter in Part II. We focus on the core part of the algorithm, producing a nested family of cloud shapes corresponding to a range of brightness thresholds. This family is then used to derive a 2D field of cloud extinction coefficient. We relate the resolution of the multi-angle measurements to the spatial accuracy of the cloud shape retrievals and determine constraints on the cloud aspect ratios required for the applicability of the algorithm. The expressions for overpass length and time derived in this study allow for estimating how much the cloud can move or change during the measurement process. We estimate biases in cloud size and position retrievals caused by the cloud’s advection during the measurements. Our accuracy estimation techniques are applied to previously published examples of clouds, both simulated and real.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1701194</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1701194</link>
        <title><![CDATA[SAU-MTF: Siamese attention U-Net with multimodal temporal fusion for accurate deforestation detection]]></title>
        <pubdate>2026-07-02T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Poovayar M. Priya</author>
        <description><![CDATA[IntroductionSatellite-based deforestation monitoring is critical for environmental sustainability and climate change mitigation. However, conventional remote sensing approaches face significant limitations in cloud-covered regions and are often inadequate for capturing temporal change dynamics, constraining their effectiveness in continuous forest surveillance.MethodsWe propose the Siamese Attention U-Net with Multimodal Temporal Fusion (SAU-MTF), a novel deep learning architecture that integrates optical (Sentinel-2) and Synthetic Aperture Radar (Sentinel-1) imagery within a tri-temporal framework. The model employs EfficientNet-based encoders and attention gates for discriminative feature extraction, alongside temporal context blocks designed to capture change dynamics across time steps. A multimodal fusion strategy is adopted to exploit the complementary strengths of SAR’s cloud-penetrating capability and the spectral richness of optical data.ResultsEvaluated on large-scale deforestation datasets, SAU-MTF achieves a classification accuracy of 94.7% and an Intersection over Union (IoU) of 0.93, outperforming existing state-of-the-art models across benchmark comparisons.DiscussionThese results demonstrate that the joint exploitation of temporal, spectral, and spatial information substantially enhances deforestation detection performance. The architecture proves especially effective in challenging environments characterized by persistent cloud cover and seasonal variability in remote forest regions, highlighting its potential for operational deployment in global forest monitoring systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1840277</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1840277</link>
        <title><![CDATA[Multi-index assessment and spatiotemporal dynamics of vegetation cover in desert regions of Xinjiang based on pixel binary models]]></title>
        <pubdate>2026-07-01T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Huihui Xin</author><author>Aierken Dawuti</author><author>Yifulayin Yusufu</author><author>Jibing Yu</author><author>Didaer Dawulietibieke</author><author>Lingyu Song</author><author>Yuehan Liu</author><author>Yunling Zhang</author><author>Songmei Ma</author>
        <description><![CDATA[Fractional vegetation cover (FVC) as a key indicator for assessing ecological degradation and recovery in arid desert regions. However, the selection of suitable vegetation indices for desert areas remains controversial because of limitations imposed by soil background interference and regional heterogeneity. This study employs a pixel-level binary classification model, integrating three commonly used vegetation indices—EVI, NDVI, and MSAVI—to systematically evaluate the spatiotemporal dynamics of FVC in Xinjiang’s desert regions from 2016 to 2025. A comparative analysis of their inversion accuracies is also conducted. The results are as follows: (1) Leveraging its multiband atmospheric and soil correction mechanisms, the EVI significantly outperformed the NDVI and MSAVI in terms of vegetation–soil discrimination capability (endpoint difference of 0.185) and inversion accuracy (R2 = 0.79), establishing itself as the optimal index for estimating FVC in Xinjiang’s desert regions. In contrast, the NDVI and MSAVI systematically overestimated FVC in areas with low vegetation density because of their sensitivity to the soil background. (2) The Junggar Basin exhibited high FVC (>50%) with high temporal variability (CV) and a predominant decreasing trend, whereas the Tarim Basin showed low FVC with low variability and a increasing trend. This study not only validates the superiority of the EVI in monitoring vegetation in arid desert regions but also maps the spatiotemporal evolution trends of vegetation coverage in Xinjiang’s desert areas, providing scientific evidence and theoretical support for regional ecological conservation and restoration practices.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1869435</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1869435</link>
        <title><![CDATA[SOE-YOLO: towards efficient and accurate small object detection in optical remote sensing imagery]]></title>
        <pubdate>2026-06-30T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Yimo Peng</author><author>Xiangyu Ge</author>
        <description><![CDATA[Small object detection in optical remote sensing imagery remains a formidable challenge due to severe background clutter, frequent missed detections, and the high computational overhead of existing models. Specifically, targets such as vehicles and ships occupy merely a few pixels, making their fine-grained details highly susceptible to degradation during network downsampling. To address these bottlenecks, we propose SOE-YOLO (Small Object Enhanced-YOLO11), a novel framework that strikes an optimal balance between accuracy and efficiency. We propose an Asymmetric Padding Down-Sampling (APDS) module to preserve spatial resolution, a C3k2-HFCE block to enhance high-frequency contrast, a Contextual Small-object Attention Fusion (CSAF) module and introduce a Dimension-Aware Selective Integration (DASI) module. Together, these components effectively bridge semantic gaps, adapt to multi-directional targets, and mitigate complex background interference. Extensive experiments demonstrate the superiority of SOE-YOLO. Compared to the baseline YOLO11n, our model achieves mAP50 improvements of 7.4%, 1.9%, and 3.7% on the VEDAI, RSOD, and NWPU VHR-10 datasets, reaching 67.8%, 90.8%, and 89.4%, respectively. Furthermore, SOE-YOLO maintains a lightweight profile with only 3.36 million parameters (corresponding to a model file size of 6.8 MB in FP32 precision and a computational cost of 10.8 GFLOPs, establishing a new state-of-the-art trade-off between detection robustness and computational efficiency.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1883314</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1883314</link>
        <title><![CDATA[Comparative evaluation of machine learning algorithms for integrated wetland modelling within a geospatial big data environment in Driefontein Grasslands of Zimbabwe]]></title>
        <pubdate>2026-06-30T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Nobert Tafadzwa Mukomberanwa</author><author>Ellen Boys</author><author>Last Keche</author><author>Kgabo Humphrey Thamaga</author>
        <description><![CDATA[IntroductionThe spatial dynamics of wetlands require advanced geospatial modelling approaches capable of capturing nonlinear ecological interactions across heterogeneous landscapes. However, many wetland studies in sub-Saharan Africa rely on single-classifier approaches and limited predictor variables, resulting in reduced classification reliability and weak ecological interpretability.MethodsThis study addresses this gap by comparatively evaluating Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Trees (CART) for integrated wetland modelling within a geospatial big data environment in the Driefontein Grasslands, Zimbabwe, a Ramsar-designated wetland ecosystem. Multi-temporal Landsat imagery acquired for 2015, 2020, and 2025 was processed using Google Earth Engine, Python 3.10, and QGIS 3.44.6 Solothurn within a scalable cloud-supported analytical framework. To improve wetland discrimination, a comprehensive suite of remotely sensed spectral indices was integrated into the modelling workflow, including NDVI, EVI, SAVI, OSAVI, MSAVI, SIPI, GCI, RECI, NDWI and MNDWI. Model performance was evaluated using Receiver Operating Characteristic (ROC) curves, Area Under the Curve (AUC) statistics, and inter-model Pearson correlation analysis.ResultsRF demonstrated superior predictive stability and discriminatory performance across all epochs (AUC = 0.880–0.891), followed by SVM (0.850–0.873), while CART exhibited comparatively lower performance (0.749–0.789) and structural divergence through negative inter-model correlations. Spectral-index analysis revealed progressive vegetation decline, hydrological fragmentation, increasing vegetation stress, and accelerated conversion of vegetated wetland surfaces to bare substrates by 2025, signalling intensifying anthropogenic disturbance and ecological degradation.DiscussionThe findings demonstrate that integrating multi-index remote sensing analytics with ensemble machine learning significantly enhances wetland detection accuracy and ecological interpretation, providing a transferable GeoAI framework for scalable wetland monitoring, ecosystem restoration planning, and evidence-based environmental policy in Africa.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1869619</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1869619</link>
        <title><![CDATA[Long-term changes in dry-season water bodies and lake-littoral land-cover structure of typical lakes in the middle-lower Yangtze and Huai River basins, China (1999–2019)]]></title>
        <pubdate>2026-06-29T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Nanbo Lu</author><author>Wenping Jin</author><author>Xiangyuan Duan</author><author>Meng Zhang</author><author>Chengsi Zhang</author>
        <description><![CDATA[Long-term monitoring of dry-season water bodies and lake–littoral land-cover structure is important for lake conservation, shoreline management, and wetland protection. Based on the Google Earth Engine platform, this study used Landsat time-series imagery from 1999 to 2019 and combined Continuous Change Detection and Classification (CCDC) with a Random Forest classifier to generate annual land-cover products for Taihu Lake, Hongze Lake, Poyang Lake, and Dongting Lake. A fixed representative date within the January–February dry-season window was used to extract dry-season land-cover maps, and all area and transition statistics were calculated within fixed lake–littoral analysis boundaries. Accuracy assessment was conducted for three representative years, namely, 1999, 2010, and 2019, corresponding to the beginning, middle, and end of the study period. The overall accuracy values were 90.10%, 91.30%, and 90.40%, respectively, with Kappa coefficients of 0.872, 0.886, and 0.875. The results revealed clear inter-lake differences in dry-season water-area change. From 1999 to 2019, Poyang Lake showed the largest decline, with a net loss of 136.95 km2 (−14.67%), whereas Taihu Lake, Hongze Lake, and Dongting Lake showed relatively small net increases of 21.07 km2 (+0.85%), 36.29 km2 (+3.39%), and 13.00 km2 (+2.75%), respectively. Land-cover transition analysis showed that conversions among water, mudflat, and field were the dominant processes of lake–littoral restructuring, including 141.40 km2 of water converted to mudflat and 89.67 km2 of mudflat converted to field. These results suggest that dry-season lake–littoral dynamics may be associated with hydrological variability, shoreline land use, and local management or restoration activities. However, these relationships should be interpreted as plausible associations rather than direct causal attribution. Overall, the CCDC–RF framework, combined with fixed dry-season extraction and transition-matrix analysis, provides a reproducible approach for monitoring long-term dry-season water-body dynamics and lake–littoral structural change.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1834812</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1834812</link>
        <title><![CDATA[Integrated spatial-contextual remote sensing classification via dual-path transformers and entropy-regularized HSIC]]></title>
        <pubdate>2026-06-25T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Tallha Akram</author><author>Faheem Ul Rehman Siddiqi</author><author>Muqaddas Gull</author><author>Amal Al‐Rasheed</author><author>Muhammad Atif Imtiaz</author><author>Ali Hamdan Alenezi</author><author>Hira Siddique</author><author>Imran Ashraf</author>
        <description><![CDATA[IntroductionRemote sensing image classification is an important task in Earth observation. However, achieving high accuracy is still challenging. This is mainly due to high-dimensional feature redundancy, large intra-class variability, and the difficulty of capturing both fine spatial details and long-range contextual information. To address these challenges, this paper proposes a unified classification framework based on a novel Multi-Scale Dual-Path Shifted Pyramid Vision Transformer (M-DSPViT).MethodsThe proposed model improves standard Vision Transformer architectures by introducing dual-path shifted patch embedding and content-adaptive attention gating. It also incorporates multi-scale feature pyramid fusion, dynamic expert routing, and gradient-based attention masking to better capture spatial and contextual features. In addition, a hybrid feature selection method (HSIC-HFS) is introduced to remove redundant information and retain discriminative features. This method combines the Hilbert-Schmidt independence criterion, Shannon entropy, and L1-regularization. The refined features are then integrated with CNN-based spatial descriptors extracted using EfficientNet through a Sequential Feature Aggregation (SFA) framework.ResultsThe proposed method is evaluated on the WHU-RS19, UC Merced, and AID benchmark datasets. It achieves state-of-the-art performance in land-use classification. The robustness and generalization ability of the model are further validated through statistical analysis, including one-way ANOVA and F-statistic testing.DiscussionThe results confirm the stability of the proposed approach across different remote sensing scenarios.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1803345</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1803345</link>
        <title><![CDATA[Temperature-index routing approach based Snowmelt–Runoff modelling in lachen basin of upper teesta catchment, Sikkim (India)]]></title>
        <pubdate>2026-06-24T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Nikita Roy Mukherjee</author><author>Akhouri Pramod Krishna</author>
        <description><![CDATA[Snow- and glacier-fed river basins in the eastern Himalaya are a significant supply of water for downstream regions but their hydrology remains tough to research due to limited ground observations, steep topography and frequent data gaps. The research area is the Lachen basin, a high-altitude sub-basin of the Upper Teesta River system in North Sikkim. The objective was to assess the capability of a temperature-index based snowmelt-runoff model coupled with a linear reservoir routing scheme to simulate discharge in a data-scarce Himalayan environment using predominantly remote sensing and gridded datasets. Snow-cover information was obtained from Moderate Resolution Imaging Spectroradiometer (MODIS) products to capture seasonal snow dynamics. Temperature, precipitation, and evapotranspiration were obtained from Famine Early Warning Systems Network Land Data Assimilation System (FLDAS) and were processed at a 10-day (dekadal) time step to coincide with observed discharge records. Effects of elevation were accounted for using a resampled TanDEM-X digital elevation model, enabling the calculation of melt in different altitude zones. Runoff was estimated utilizing a simple water balance approach and routed to account for delayed flow response within the basin. The model was calibrated and validated using discharge data from the Lachen gauging station under the Central Water Commission (CWC). The model could reproduce the seasonal variations of discharge with higher flows in the pre-monsoon snowmelt phase and peak discharge during the monsoon period. The validation findings show good performance of the model with a Nash–Sutcliffe efficiency (NSE) of 0.843, coefficient of determination (R2) of 0.847 and RMSE of 92.97 m3 s−1. The comparative comparison with the standard SRM framework indicated better runoff modelling and hydrograph depiction in the glacierized Himalayan basin. Some discrepancies were noted during high-flow circumstances, which are likely related to uncertainties in precipitation inputs and simplified process representation, but results suggest that the model offers a reliable prediction of discharge in glacier-fed basins. The work demonstrates the efficacy of combining remote sensing data with a temperature-index routing approach for hydrological modelling in data-scarce Himalayan regions.]]></description>
      </item>
      </channel>
    </rss>