<?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>2026-07-08T13:09:52.266+00:00</pubDate>
        <ttl>60</ttl>
        <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.2026.1813566</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.2026.1804569</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.2026.1883314</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.2026.1869435</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.2026.1869619</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><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1822070</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1822070</link>
        <title><![CDATA[Fine-grained crop classification from satellite image time series by boosting rare-class representations and enforcing global semantic consistency]]></title>
        <pubdate>2026-06-22T00:00:00Z</pubdate>
        <category>Methods</category>
        <author>Anqi Wang</author><author>Jiacheng Ge</author><author>Zhe Dong</author><author>Junchao Wu</author><author>Wei Guo</author>
        <description><![CDATA[Accurate and timely fine-grained crop type classification from satellite image time series is crucial for large-scale agricultural monitoring and decision support in food-security management. However, fine-grained classification remains challenging due to extreme class imbalance and high inter-crop spectral similarity, especially when rare crops occupy only small and fragmented parcels. We propose a rare-class-aware framework with global semantic consistency regularization for fine-grained crop classification from Sentinel-2 multispectral time series. Built on a spatiotemporal encoder–decoder backbone, the framework combines rare-class-aware patch sampling with spatiotemporal perturbations to strengthen minority-class representations, and a global semantic consistency regularization based on patch-level class proportion estimation to align patch composition with pixel-wise predictions. Experiments on the H2Crop benchmark (France, 2022–2023), which contains over 1 million annotated parcels and 101 fine-grained crop types, validate the proposed strategy. Our method achieves a mean F1-score of 36.72% and an IoU of 27.82%, consistently outperforming state-of-the-art approaches, with improvements of 4.38 percentage points in F1-score and 4.00 percentage points in IoU over the strongest competitor. These results demonstrate strong potential for reliable rare-crop recognition and fine-grained agricultural monitoring in large, highly imbalanced landscapes.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1770598</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1770598</link>
        <title><![CDATA[Extensive review of evapotranspiration estimation methodologies over a semi-arid region]]></title>
        <pubdate>2026-06-19T00:00:00Z</pubdate>
        <category>Systematic Review</category>
        <author>Vinayaka Shankar Gargi</author><author>Surendar Manickam</author>
        <description><![CDATA[Evapotranspiration (ET) is a key element in the hydrological cycle. It has a high impact on climate studies, agricultural productivity, and water resource management. Despite its importance, the accurate estimation of ET over semi-arid areas continues to be difficult, mainly due to heterogeneity in land surface properties and large variations in weather patterns. This study follows the PRISMA framework to systematically review 174 full-text publications from 1971 to 2025. The review summarizes both the advantages and disadvantages of remotely sensed ET estimation techniques, with detailed description on the Residual Approach to Surface Energy Balance and Simplified Empirical Regression. Key models reviewed include SEBI, S-SEBI, SEBAL, METRIC, SEBS, SSEB-op, the Modified Priestely-Taylor Method, and VI-Ts Triangle/trapezoidal space methods. The review critically goes through the diverse data source and their needs for enhancement in the ET estimation, particularly for semi-arid regions. Moreover, it discusses the different types of remote sensing data available for enhancing the accuracy of ET estimation, especially for semi-arid areas, and it discusses the variety of issues and uncertainties associated with remote sensing ET models, including terrain feature precision and near-surface meteorological data gaps. Finally, this study addresses future trends and opportunities in remote sensing technology and methodology that will eventually help to overcome some of the limitations of current remote sensing methods for improving ET estimation and ultimately enhance the management of our world’s water resources.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1770166</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1770166</link>
        <title><![CDATA[Using non-vegetated soil mosaics for soil property modelling to compare Google Earth Engine and THEIA platforms across Sminja Plain, Tunisia]]></title>
        <pubdate>2026-06-17T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Mukhtar Adamu Abubakar</author><author>Youssef Fouad</author><author>Hamouda Aïchi</author><author>Didier Michot</author><author>Lucie Martin</author><author>Hayfa Zayani</author><author>Emmanuelle Vaudour</author>
        <description><![CDATA[This study examines the potential of Sentinel-2 (S2) temporal mosaics (TM) of non-vegetated soils to enhance soil property mapping in the semi-arid Sminja Plain, Tunisia (480 km2). Using multi-season data from 2019 to 2023, TMs were generated with two processing platforms, Google Earth Engine (GEE) and THEIA, and their predictive performances were compared. Non-vegetated soils were isolated using thresholds of NDVI < 0.35 and NBR2 < 0.09 to optimise non-vegetated soil extraction. Key soil properties, including electrical conductivity (EC), pH, soil organic carbon (SOC), base saturation (BS), exchangeable bases (K, Ca, and Na), granulometric fractions, and soil moisture contents (at field capacity and permanent wilting point), were analysed from 215 georeferenced samples systematically distributed across the study area. Random Forest (RF) models were calibrated using K-fold cross-validation, and their predictive performances were evaluated through RMSE, RPD, and RPIQ metrics. Results indicate that both platforms effectively predicted most of the inherent soil properties (SOC, CaCO3, Ca, BS, granulometric fractions, and soil moisture content) with RPIQ values over 1.7. Conversely, predictions for dynamic soil properties (pH, EC, K, Na, and P2O5) were less or non-reliable, with RPIQ below 0.8. Seasonal mosaics had a minor effect on model performance, while platform choice showed only slight differences, with GEE performing marginally better in some cases. This highlights the limitations of the TM and RF models for certain dynamic soil properties in such environments. These findings emphasise the importance of multi-season non-vegetated soil mosaics for monitoring semi-arid soils and provide insights to support sustainable land management and agricultural planning.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1818592</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1818592</link>
        <title><![CDATA[Evaluation of operational satellite-based disturbance detection products in Brazilian primary forests for the years 2023 and 2024]]></title>
        <pubdate>2026-06-16T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Peter Potapov</author><author>Svetlana Turubanova</author><author>Marcos Rosa</author><author>Lana Teixeira</author><author>Julia Shimbo</author><author>Viviana Zalles</author><author>Michelle J. Sims</author><author>Radost Stanimirova</author><author>Andre Lima</author><author>Elizabeth Goldman</author><author>Nancy Harris</author><author>Fred Stolle</author>
        <description><![CDATA[Operational forest monitoring is essential for the effective implementation of national and international initiatives to reduce deforestation and forest degradation. Such monitoring systems are especially important within Brazilian humid tropical primary forests, where they support enforcement of national policies to prevent deforestation. Several satellite-based forest disturbance monitoring systems are operating in Brazil, including MapBiomas Alerta (MBA), Tree Cover Loss supported by Global Forest Watch (TCL), and Tropical Moist Forest developed by the European Commission’s Joint Research Centre (TMF). These systems differ in their forest disturbance definitions, input satellite data, and change detection methodologies. As a result, their annual estimates of primary forest disturbance are not fully consistent, which complicates the implementation of forest conservation policy and introduces uncertainties and potential bias in greenhouse gas emissions accounting. In this study, we followed good practice recommendations to evaluate the performance of these monitoring products to detect humid tropical primary forest disturbances in 2023 and 2024 using a probability reference sample. We compared the map-based and sample-based disturbance areas for each product and estimated their sensitivity and precision for primary forest disturbance detection. Our analysis showed that the MBA product mapped 64%–65% of the sample-based reference deforested area while maintaining the highest mapping precision among the three systems. The TCL product detected the highest percentage of the reference deforested area (82%–94%), while maintaining high precision for mapping high-severity, stand-replacement disturbances. TMF outperformed other products in capturing low-severity disturbances. The detailed comparative evaluation of the three operational monitoring systems highlights their respective strengths and limitations and explains the differences in forest disturbance reporting. Our results provide guidance for researchers, policymakers, and practitioners in selecting the most appropriate products for specific applications.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1788857</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1788857</link>
        <title><![CDATA[Spectral detection of basal stem rot in oil palm plantations using UAV hyperspectral imagery, deep learning segmentation, and machine learning classification: a case study at the sembawa plantation]]></title>
        <pubdate>2026-06-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Rakyan Paksi Nagara</author><author>Masita Dwi Mandini Manessa</author><author> Rokhmatuloh</author><author>Kuncoro Adi Pradono</author><author>Fajar Dwi Pamungkas</author><author>Anisya Feby Efriana</author><author>Farida Ayu</author><author>Charlos Togi Stevanus</author>
        <description><![CDATA[Detection of Basal Stem Rot (BSR) caused by Ganoderma boninense remains difficult in oil palm disease management because spectral and physiological changes in the canopy accompany infection well before palms enter terminal decline. This study developed a pipeline combining UAV‐borne hyperspectral imagery at 5 cm spatial resolution, deep learning-based instance segmentation, machine learning classification, and spatial analysis to discriminate symptomatic BSR‐affected palms from healthy ones at the individual-tree scale, map disease distribution, and explore associations with environmental variables. Ground truth was established through field observation conducted with plantation biologist researchers: infected trees were identified by physical canopy symptoms including chlorosis, necrosis, reduced crown density, and premature frond collapse, assessed using a composite three-indicator scoring protocol. A Mask R‐CNN model delineated individual tree canopies with 89.0% Average Precision (AP50). A Support Vector Machine classifier applied to the full 95-band hyperspectral dataset achieved 86.50% overall accuracy (kappa = 0.82) in pixel‐level classification. Tree‐level validation against field‐assessed labels yielded 84.3% accuracy and kappa = 0.71. Spatial analysis identified five statistically significant local hotspots of infection (Getis‐Ord Gi*), whereas global clustering was non-significant (Z = 1.27, p = 0.204). Associations between BSR incidence and eight environmental variables were weak and non‐significant in this exploratory analysis, with soil pH showing the highest positive association (r = 0.142) and soil nitrogen the strongest negative association (r = −0.151). The approach produces spatially explicit discrimination of symptomatic BSR‐affected trees from healthy ones, with scope conditions defined for future extension.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1828883</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1828883</link>
        <title><![CDATA[Integrated sediment mapping and evaluation in riverbed considering fluvial geomorphic diversity]]></title>
        <pubdate>2026-06-08T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Zuisen Li</author><author>Zhen Tian</author><author>Xiaoming Wang</author><author>Yaxue Wang</author><author>Yuewen Sun</author><author>Zhimin Wu</author><author>Muning Zhang</author><author>Xiaodong Cui</author>
        <description><![CDATA[A crucial indicator of hydrodynamic conditions, sediment transport systems, and geomorphic evolution is riverbed sediment. Hydraulic engineering, channel upkeep, and ecological management all depend on accurate sediment classification. Because of their intricate geomorphology and dynamic hydrodynamic forces, riverine systems show more spatial heterogeneity than comparatively stable marine habitats. It is challenging to adapt traditional mapping of the link between sediment types and acoustic signal characteristics based on a single resolution or uniform scale to the riverbed settings present in river basins. This study suggests a multi-resolution, multi-scale framework for riverbed sediment classification that incorporates both local detail and broad structural elements in order to overcome these limitations. The geomorphons landform identification approach is presented as a crucial instrument for describing the spatial distribution of riverbed silt due to the complexity of riverbed geomorphology. Bathymetric, backscatter, and geomorphic characteristics are combined across several resolutions and scales to create a hierarchical feature-extraction approach. To find stable and discriminative variables, an iterative tree-based feature selection technique is used. Three supervised classification models are assessed using multibeam and field sampling data from the Fuchun River Basin. The results show that the suggested method continuously enhances classification performance for all models. The overall accuracy of the Random Forest classifier increases by about 5%. The findings show that using multi-resolution and multi-scale information enhances riverbed classification’s resilience and accuracy.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1703257</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1703257</link>
        <title><![CDATA[Decline in satellite-derived primary production in the north-east Atlantic driven by changes in sea surface temperature and mixed layer depth]]></title>
        <pubdate>2026-06-05T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Gavin H. Tilstone</author><author>Peter E. Land</author>
        <description><![CDATA[Phytoplankton Primary Production supports most of the marine ecosystem and is highly sensitive to changing environmental pressures. There is much debate about whether marine primary production is increasing or decreasing and what environmental parameters may be driving these changes. We analysed a 21-year time-series of net primary production (NPP) computed from Ocean Colour Climate Change Initiative (OC-CCI) data spanning September 1997-December 2018, focusing on areas of similar phenology, climatology, and annual NPP in the north-east Atlantic Ocean. Across the entire area, NPP increased from 1998 to 2003, followed by a significant decline until 2018. This pattern was predominant in north-western European coastal waters and specific areas of the English Channel, Irish Sea, North Sea and Norwegian Sea, where it was related to changes in sea surface temperature and mixed layer depth.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frsen.2026.1741055</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frsen.2026.1741055</link>
        <title><![CDATA[Spatiotemporal signature of land cover change: linking albedo and land surface temperature dynamics in Iran]]></title>
        <pubdate>2026-06-04T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Omid Reza Kefayat Motlagh</author><author>Hamid Nazaripour</author><author>Sanaz Manavipour</author><author>Vahid Shafaie</author><author>Majid Movahedi Rad</author>
        <description><![CDATA[The interaction between Land Surface Temperature (LST) and albedo plays a crucial role in regulating surface energy dynamics and environmental variability. This study presents the first comprehensive, nation-scale diagnostic analysis of the LST-albedo relationship in Iran, using daily MODIS MCD43A4 and MOD11A1 datasets spanning 8035 days from 1 January 2001, to 31 December 2022. Data preprocessing involved standardizing the spatial resolution of 500-m albedo data to match the 1000-m LST data using the reshape function in MATLAB. Seasonal and annual mean values were computed for 1,884,077 pixels, followed by statistical correlation analysis through the calculation of the correlation coefficient (r) and coefficient of determination (r2), and corresponding p-values. We introduce a spatiotemporal correlation-based diagnostic framework. The results reveal that distinct correlation patterns (positive vs. negative) serve as robust diagnostic signatures for specific land cover changes: positive correlations in desiccated lakes and wetlands (e.g., Lake Urmia) signal surface aridification, while strong negative correlations in highlands are indicative of snow-cover decline via the snow-albedo feedback, where declining albedo due to snow cover reduction was accompanied by increasing LST, particularly in winter. These findings establish that LST-albedo correlation patterns are not merely descriptive statistics but a scalable diagnostic tool. This framework provides a powerful transferable approach for monitoring critical environmental changes, such as drought intensification and snowpack loss, in Iran and similar arid to semi-arid regions worldwide.]]></description>
      </item>
      </channel>
    </rss>