Remote Sensing

25 pages, 14247 KB

Open AccessArticle

Sea Surface Current Vector Reconstruction from Multitemporal Sentinel-1 Doppler Observations: A Trajectory-Crossing Approach with Spatial Registration

by Wenjia Zhao, Haimei Mo, Yawei Zhao, Jincheng Deng, Lebao Yang and Jinsong Chong

Remote Sens. 2026, 18(18), 3192; https://doi.org/10.3390/rs18183192 (registering DOI) - 16 Sep 2026

Abstract

Synthetic aperture radar (SAR) provides high-resolution observations of radial sea surface currents. By combining radial currents observed from different viewing directions, the trajectory-crossing method can reconstruct the sea surface current vector field. In practice, observations from ascending and descending passes are acquired at [...] Read more.

Synthetic aperture radar (SAR) provides high-resolution observations of radial sea surface currents. By combining radial currents observed from different viewing directions, the trajectory-crossing method can reconstruct the sea surface current vector field. In practice, observations from ascending and descending passes are acquired at different times, so the spatial structure of the surface current field may evolve between acquisitions. Directly combining multitemporal observations can therefore introduce spatial mismatch and reduce reconstruction accuracy. This study proposes a trajectory-crossing method for reconstructing sea surface current vectors from multitemporal Sentinel-1 Doppler observations. Maximum cross-correlation (MCC) is applied to gradient images of the radial current fields to estimate displacement and spatially register observations acquired at different times before vector reconstruction. The method is evaluated using Sentinel-1 data acquired over the Gulf Stream region and compared with geostrophic currents from the Copernicus Marine Environment Monitoring Service (CMEMS), Surface Water and Ocean Topography (SWOT) observations, and Global Drifter Program (GDP) drifter measurements. Results show that the proposed method reduces mismatch effects and improves the accuracy and stability of sea surface current vector reconstruction. It provides a practical approach for deriving surface current vector fields from multitemporal SAR Doppler observations. Full article

(This article belongs to the Special Issue Remote Sensing of Wave Dynamics and Hydrodynamics in Marine Environments)

26 pages, 4929 KB

Open AccessArticle

Unpacking the Fragmentation–Ecology Nexus: Spatial Heterogeneity, Nonlinear Responses, and Associated Ecological Factors Across Urban Agglomerations in the Yellow River Basin

by Meiling Zhou, Meiling Gao, Zhenhong Li, Xinxin Fu, Jiahao Ma and Lili Chen

Remote Sens. 2026, 18(18), 3191; https://doi.org/10.3390/rs18183191 (registering DOI) - 16 Sep 2026

Abstract

Ecological quality and landscape fragmentation are closely linked in rapidly urbanizing regions, yet their relationship across different urbanization contexts remains insufficiently understood. This study examined the spatiotemporal dynamics and coupling between the Remote Sensing Ecological Index (RSEI) and Landscape Fragmentation Index (LFI) across [...] Read more.

Ecological quality and landscape fragmentation are closely linked in rapidly urbanizing regions, yet their relationship across different urbanization contexts remains insufficiently understood. This study examined the spatiotemporal dynamics and coupling between the Remote Sensing Ecological Index (RSEI) and Landscape Fragmentation Index (LFI) across the Yellow River Basin Urban Agglomerations from 2000 to 2020. Geographically weighted regression, quantile-based mean-response analysis, and XGBoost–SHAP were applied to characterize spatial heterogeneity, nonlinear responses, and ecological quality drivers. Mean RSEI increased from 0.401 to 0.463, whereas mean LFI increased slightly from 0.474 to 0.486. Long-term trajectories differed across urbanization classes: NUr zones generally showed ecological improvement, NU zones exhibited declining RSEI and a significant reversal in LFI around 2013, and EU zones showed declines in both indices. Core–periphery profiles further revealed regionally heterogeneous and asynchronous RSEI–LFI responses. RSEI–LFI relationships exhibited strong spatial non-stationarity and nonlinear responses, with positive coupling in the slope-based model more prevalent in NUr zones and negative coupling dominant in urbanized zones. Precipitation was the dominant contributor to RSEI spatial variation, whereas topographic conditions and climate trends were more influential in the slope-based model. These findings highlight that fragmentation–ecology relationships are context-dependent rather than universally negative. Full article

(This article belongs to the Section Ecological Remote Sensing)

► Show Figures

Figure 1

32 pages, 8240 KB

Open AccessArticle

Multi-Scale Validation of Satellite-Based Precipitation Products and Their Impacts on Hydrological Simulation in a Humid Mountainous Basin

by Zhuang Niu, Helong Wang, Dingtao Shen, Shenjun Lu and Shizong Zheng

Remote Sens. 2026, 18(18), 3190; https://doi.org/10.3390/rs18183190 (registering DOI) - 16 Sep 2026

Abstract

Accurate precipitation information is crucial for hydrological simulation and water resources management, especially in humid mountainous regions where complex terrain and spatially heterogeneous rainfall introduce considerable uncertainties. Satellite-based precipitation products provide important data sources for hydrological applications; however, their reliability and impacts on [...] Read more.

Accurate precipitation information is crucial for hydrological simulation and water resources management, especially in humid mountainous regions where complex terrain and spatially heterogeneous rainfall introduce considerable uncertainties. Satellite-based precipitation products provide important data sources for hydrological applications; however, their reliability and impacts on runoff simulations remain uncertain across different spatial and temporal scales. This study presents a multi-scale validation of four precipitation products, including GSMaP, PERSIANN, GPM IMERG, and CLDAS, and evaluates their effects on hydrological simulation in the Oujiang River Basin, a typical humid mountainous basin in southeastern China. Daily precipitation estimates from 2015 to 2020 were compared with gauge observations using statistical metrics and precipitation event indicators. The hydrological applicability of each product was further assessed by driving a semi-distributed Xin’anjiang model, with evaluations conducted at the basin outlet, seasonal periods, extreme rainfall events, and internal subbasins. Results showed that CLDAS achieved the best overall agreement with gauge observations, with lower systematic bias and higher capability in detecting precipitation variability. Satellite-only products exhibited larger uncertainties, particularly during extreme rainfall events and in areas with complex terrain. These precipitation uncertainties were further propagated into runoff simulations, leading to differences in hydrological performance among products. CLDAS-driven simulations showed the highest accuracy, achieving R², NSE, and KGE values of 0.706, 0.681, and 0.815, respectively, which were comparable to simulations driven by gauge-based precipitation. Multi-scale analysis revealed that product performance varied among subbasins due to differences in topography, rainfall characteristics, and human regulation. This study demonstrates the importance of multi-scale validation for quantifying uncertainties in satellite-based precipitation products and improving their application in hydrological modeling over mountainous regions. Full article

(This article belongs to the Special Issue Advances in Satellite-Based Precipitation Products: Validation, Uncertainty, Artificial Intelligence and Hydrological Applications)

► Show Figures

Figure 1

29 pages, 9711 KB

Open AccessArticle

Low-Cost Geological Reconnaissance for Artisanal and Small-Scale Mining: RGB–HSV Analysis of Rendered Google Earth Imagery in Arid Copper-Prospective Terrains of Chile and Balochistan

by Horst Kutsch and Kentaro Takasaki

Remote Sens. 2026, 18(18), 3189; https://doi.org/10.3390/rs18183189 (registering DOI) - 16 Sep 2026

Abstract

Advanced multispectral and hyperspectral remote sensing supports mineral and alteration mapping, but its imagery, specialist expertise and validation requirements may remain inaccessible to artisanal and small-scale mining operators during first-pass evaluation. This study evaluates how much defensible geological reconnaissance information can be extracted [...] Read more.

Advanced multispectral and hyperspectral remote sensing supports mineral and alteration mapping, but its imagery, specialist expertise and validation requirements may remain inaccessible to artisanal and small-scale mining operators during first-pass evaluation. This study evaluates how much defensible geological reconnaissance information can be extracted from rendered Google Earth imagery without interpreting display color as mineralogical evidence. Google Earth Pro RGB exports displaying Airbus Pléiades imagery were processed using a reproducible workflow combining preprocessing, RGB–HSV transformation, color-class delineation, spatial-pattern assessment and lineament analysis. Image-derived classes were treated as color-defined surface indicators and evaluated against documented geological and structural evidence. Two Chilean IOCG-related reference cases represented contrasting geometries: Farellon displayed narrow, structurally aligned patterns, whereas El Morado displayed a broader, discontinuous corridor-scale distribution. Two underexplored Chilean targets displayed corresponding linear and patchy patterns. A documented skarn occurrence served as a contrasting mineral-system case. Kabul Koh and Ziarat Malik Karkam in Balochistan’s porphyry Cu–Au-prospective Chagai magmatic belt were used to test cross-regional and cross-mineral-system applicability. Across the cases, the workflow delineated contrasting surface-pattern geometries and their spatial relationships with interpreted structures without inferring mineral identity or deposit type from the RGB–HSV classes alone. The method therefore provides a low-cost, constraint-conditioned reconnaissance and target-prioritization procedure for arid copper-prospective terrains, supporting preliminary reassessment of existing or abandoned artisanal workings. Full article

(This article belongs to the Special Issue Remote Sensing for Mineral Exploration: Current Progress and Future Vision (2nd Edition))

25 pages, 44926 KB

Open AccessArticle

The Evolution of Land Subsidence Under the New Water Regime in the North China Plain: A TS-InSAR and Spatiotemporal Pattern Analysis

by Binjia Wang, Tianfei Chen, Jusong Shi, Baoping Wen, Beibei Chen, Dexin Meng, Jiuxin Yan, Haigang Wang, Liqiang Tang, Xiaoming Li and Lian Xia

Remote Sens. 2026, 18(18), 3188; https://doi.org/10.3390/rs18183188 (registering DOI) - 16 Sep 2026

Abstract

The North China Plain (NCP) has entered a “New Water Regime” driven by water diversions, stringent groundwater management, and climatic fluctuations, resulting in the widespread recovery of regional groundwater levels. How land subsidence has responded spatiotemporally to these interventions remains unclear. To quantify [...] Read more.

The North China Plain (NCP) has entered a “New Water Regime” driven by water diversions, stringent groundwater management, and climatic fluctuations, resulting in the widespread recovery of regional groundwater levels. How land subsidence has responded spatiotemporally to these interventions remains unclear. To quantify the regional hydrogeological responses, we integrated Time-Series Interferometric Synthetic Aperture Radar (TS-InSAR) observations spanning 2016–2023 with weighted centroid tracking and Emerging Hot Spot Analysis (EHA) based on a Space-Time Cube. Centroid tracking indicated that the regional subsidence center remained spatially stable without significant directional drift. In the western and southern regions, Persistent and Intensifying Cold Spots dominated, corresponding to ground stabilization and rebound. In the central-eastern centers, 26.80% and 6.47% of the statistically significant clustering area were Persistent and Intensifying Hot Spots, reflecting continuous localized compaction, with Mann–Kendall and Sen’s slope analyses indicating a decelerating trend within these clusters. A further 4.92% and 9.63% were Diminishing and Historical Hot Spots, indicating reduced clustering after 2019. Overall, subsidence has decelerated markedly across most of the plain, yet compaction inertia in thick clay layers sustains localized hot spots despite rebounding groundwater levels. This time-lag response implies that short-term water-level recovery cannot immediately reverse subsidence, necessitating sustained groundwater management across the NCP. Full article

► Show Figures

Figure 1

35 pages, 27237 KB

Open AccessArticle

Unsupervised Scale-Conditioned Hyperspectral and Multispectral Image Fusion via a Frequency–Spatial Dual-Domain Network

by Peng Tang, Ke Zheng, Jiaxin Li, Haoyang Yu and Xu Sun

Remote Sens. 2026, 18(18), 3187; https://doi.org/10.3390/rs18183187 (registering DOI) - 16 Sep 2026

Abstract

Hyperspectral–multispectral image fusion reconstructs high-spatial-resolution hyperspectral images (HR-HSIs) by combining low-resolution hyperspectral images (LR-HSIs) with high-resolution multispectral images (HR-MSIs). Many methods only support integer resolution ratios; when the LR-HSI/HR-MSI ratio is fractional, inputs are often resampled to a nearby integer ratio, altering observations [...] Read more.

Hyperspectral–multispectral image fusion reconstructs high-spatial-resolution hyperspectral images (HR-HSIs) by combining low-resolution hyperspectral images (LR-HSIs) with high-resolution multispectral images (HR-MSIs). Many methods only support integer resolution ratios; when the LR-HSI/HR-MSI ratio is fractional, inputs are often resampled to a nearby integer ratio, altering observations and introducing interpolation error. We propose SCDF-Net, an unsupervised Scale-Conditioned Dual-domain Fusion Network that treats the spatial ratio as an explicit conditioning variable and fuses directly on native grids without HR-HSI labels. A degradation network first estimates the point spread function and spectral response function in a self-supervised manner; the learned operators are then frozen as physical priors. Conditioned on a continuous scale embedding, SCDF-Net integrates HSI spectral features and MSI spatial features through coupled frequency- and spatial-domain branches, trained with dual observation-domain consistency and spectral/frequency regularizations. On four benchmarks, baseline comparisons at scale factors ×1.5, ×2.0, ×2.4, and ×4.0 show that SCDF-Net obtains the lowest SAM on all datasets and improves PSNR/RMSE in most reported settings, with clear advantages under fractional scale factors. In addition, the multi-scale self-evaluation is extended to ×5.0 and ×6.0 to assess robustness under more severe spatial degradation. Full article

(This article belongs to the Special Issue Innovations in Hyperspectral Image Processing: Advancing Image Generation, Denoising, Fusion Techniques and Beyond)

► Show Figures

Figure 1

41 pages, 29621 KB

Open AccessArticle

Class-Specific Interpretation and Validation of Optical and SAR Sensor Contributions in Multi-Sensor Land-Cover Classification Using SHAP and Leave-One-Sensor-Out Ablation

by Jeonghee Lee, Kwangseob Kim and Kiwon Lee

Remote Sens. 2026, 18(18), 3186; https://doi.org/10.3390/rs18183186 - 16 Sep 2026

Abstract

This study benchmarks four classifiers—Random Forest (RF), Classification and Regression Trees (CART), Support Vector Machine (SVM), and Gradient Tree Boosting (GTB)—on an identical 16-feature KOMPSAT-3/5 and Sentinel-1/2 stack harmonized to a common 2.8 m grid within Google Earth Engine. RF and GTB reached [...] Read more.

This study benchmarks four classifiers—Random Forest (RF), Classification and Regression Trees (CART), Support Vector Machine (SVM), and Gradient Tree Boosting (GTB)—on an identical 16-feature KOMPSAT-3/5 and Sentinel-1/2 stack harmonized to a common 2.8 m grid within Google Earth Engine. RF and GTB reached overall accuracies of 92.4% and 92.8%, separating them from the unconstrained CART under family-wise correction and from the linear-kernel SVM under false-discovery-rate control. Class-specific SHAP was cross-interpreted against permutation importance, feature-correlation analysis, and a leave-one-sensor-out (LOSO) ablation, with SHAP and permutation-importance rankings in broad agreement (Spearman ρ = 0.72–0.92). The central contribution is to characterize two conditions—strong within-sensor collinearity and class-conditional information concentration—under which feature-level attribution and sensor-level necessity diverge. In the Bare Land class, no individual Sentinel-2 SWIR band ranks among the top three by SHAP, yet withholding the Sentinel-2 group produces the largest class-wise degradation observed (ΔF1 = 0.102 for RF and 0.130 for GTB), consistent with attribution dilution across the collinear SWIR1–SWIR2 pair (r = 0.97). Because none of the sixteen ablation contrasts survives multiplicity correction with a sample size of 250 (n = 250), these contrasts are reported as effect-size estimates rather than confirmatory tests. Full article

(This article belongs to the Special Issue Explainable and Trustworthy AI for Earth Observation Applications and Geospatial Science)

► Show Figures

Figure 1

34 pages, 6321 KB

Open AccessArticle

Retrieval of Optically Active and Inactive Water Quality Parameters Using Remote Sensing and Machine Learning: Evidence from Water Hyacinth-Infested Lake Tana, Ethiopia

by Lakachew Y. Alemneh, Daganchew Aklog, Ann Van Griensven, Minychl G. Dersseh, Goraw Goshu, Seleshi Yalew, Demesew A. Mhiret, Sisay B. Asress, Tigistu Wassie Agegnehu, Shawl Abebe Desta and Samuel Berihun Kassa

Remote Sens. 2026, 18(18), 3185; https://doi.org/10.3390/rs18183185 - 16 Sep 2026

Abstract

Monitoring water quality is critical for protecting freshwater ecosystems and supporting sustainable water resource management. Lake Tana, Ethiopia’s largest freshwater lake, faces increasing agricultural and urban pressures, while conventional monitoring remains costly and spatially constrained. This study developed an integrated Sentinel-2 remote sensing [...] Read more.

Monitoring water quality is critical for protecting freshwater ecosystems and supporting sustainable water resource management. Lake Tana, Ethiopia’s largest freshwater lake, faces increasing agricultural and urban pressures, while conventional monitoring remains costly and spatially constrained. This study developed an integrated Sentinel-2 remote sensing and machine learning framework to estimate chlorophyll-a (Chl-a), turbidity (TU), total nitrogen (TN), and total phosphorus (TP) using 858 in situ observations and Google Earth Engine. Random Forest (RF), Extreme Gradient Boosting (XGB), Artificial Neural Networks (ANN), and Support Vector Regression (SVR) were evaluated using spectral bands, band combinations, and indices. RF provided the best predictions for Chl-a (R² = 0.94 ± 0.01; RMSE = 2.11 ± 0.18 µg L⁻¹; MARE = 5%) and TP (R² = 0.91 ± 0.01; RMSE = 0.26 ± 0.01 mg L⁻¹; MARE = 8.7%), whereas XGB performed best for TU (R² = 0.93 ± 0.01; RMSE = 5.17 ± 0.43 NTU; MARE = 7%) and TN (R² = 0.94 ± 0.02; RMSE = 0.18 ± 0.02 mg L⁻¹; MARE = 9.9%). The strong predictive performance of RF and XGB across both optically active and inactive parameters demonstrates the capability of the framework to capture complex spectral water quality relationships and support spatially continuous assessment. Significant seasonal differences (p < 0.001) showed higher dry season Chl-a (137.1%) and higher wet season TP (21.7%), TU (7.5%), and TN (3.9%). Long-term paired observations further indicated increases in Chl-a (73.7%), TN (30%), and TP (14.3%) from December 2016 to December 2025 (p < 0.001). Spatial hotspot analysis revealed strong clustering of TU, TN, and TP, particularly around tributary mouths and nearshore areas, highlighting priority zones for monitoring and intervention. Overall, integrating field observations, Sentinel-2 imagery, and machine learning provides an accurate, scalable, and cost-effective approach for monitoring diverse water quality parameters. The framework offers a transferable solution for strengthening freshwater monitoring in data-scarce regions and supporting sustainable management of lakes under increasing water quality pressures. Full article

(This article belongs to the Special Issue Advanced Remote Sensing of Aquatic Environments: Water Quality, Ecosystem Dynamics, and Environmental Change)

► Show Figures

Figure 1

24 pages, 3660 KB

Open AccessArticle

Quantifying the Spatio-Ecological Context of Urban Nature-Based Solutions Across European Cities

by Andrew Ikingura, Barbara Sowińska-Świerkosz, Dagmara Kociuba, Hai-Ying Liu, Elina Dace, Fabiano Lemes de Oliveira, Raimund Kemper and Anna Giulia Castaldo

Remote Sens. 2026, 18(18), 3184; https://doi.org/10.3390/rs18183184 - 16 Sep 2026

Abstract

Nature-Based Solutions (NBS) are increasingly implemented to address urban environmental challenges, yet the surrounding spatial context in which they are embedded may influence the conditions supporting their ecological functioning. This study applied an integrated remote sensing-based spatial diagnostic framework combining Sentinel-2 spectral indices [...] Read more.

Nature-Based Solutions (NBS) are increasingly implemented to address urban environmental challenges, yet the surrounding spatial context in which they are embedded may influence the conditions supporting their ecological functioning. This study applied an integrated remote sensing-based spatial diagnostic framework combining Sentinel-2 spectral indices and land-cover composition metrics to characterize and compare the surrounding environments of five NBS sites in Oslo, Riga, Milan, St. Gallen, and Lublin. The Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), and Normalized Difference Built-Up Index (NDBI) were analyzed within 100 m, 300 m, and 500 m buffer zones alongside land-cover composition assessments. The analysis revealed substantial variation in vegetation greenness, moisture conditions, built-up intensity, and landscape composition. Three spatial-context profiles were identified: low-density/peri-urban settings, exemplified by the Riga NBS site with consistently high NDVI (0.483–0.374), positive NDMI (0.230–0.171), and strongly negative NDBI (−0.230 to −0.171); mixed urban settings, represented by the Oslo, Lublin, and St. Gallen NBS sites; and dense urban settings, represented by the Milan NBS site, which exhibited the lowest NDVI (0.197–0.124), declining NDMI (0.054 to −0.014), and positive NDBI beyond 300 m (0.001–0.014). These findings demonstrate that surrounding landscape characteristics provide a meaningful basis for distinguishing urban NBS settings. The proposed replicable framework can support context-sensitive planning by identifying areas where complementary landscape-scale measures, including de-paving, strategic greening, and improved landscape connectivity, may be considered to strengthen the broader environmental conditions surrounding NBS. Full article

(This article belongs to the Section Urban Remote Sensing)

27 pages, 3728 KB

Open AccessArticle

Deep Learning-Based Monitoring of Photovoltaic Power Plant Expansion and Assessment of Albedo-Driven Shortwave Energy Changes

by Yongzhen Cai, Hu Zhang, Jingtian Pu, Lei Cui, Zimeng Yan, Qiong Wu, Jiawen Chen and Peng Guo

Remote Sens. 2026, 18(18), 3183; https://doi.org/10.3390/rs18183183 - 16 Sep 2026

Abstract

Large-scale photovoltaic (PV) power plants are expanding rapidly across arid desert regions, driving land-cover transformations and associated changes in surface properties. Most existing remote sensing studies focus primarily on mapping PV distribution, while quantitative assessments of PV-induced land-cover transitions and associated surface property [...] Read more.

Large-scale photovoltaic (PV) power plants are expanding rapidly across arid desert regions, driving land-cover transformations and associated changes in surface properties. Most existing remote sensing studies focus primarily on mapping PV distribution, while quantitative assessments of PV-induced land-cover transitions and associated surface property changes remain limited. This study develops an integrated assessment framework that combines time-series Sentinel-2 imagery and Moderate Resolution Imaging Spectroradiometer (MODIS) Bidirectional Reflectance Distribution Function (BRDF) prior parameters. Three semantic segmentation models are compared for PV extraction, with independent generalization validation conducted over desert areas in Xinjiang. Constrained by coarse-resolution BRDF products, 10 m broadband white-sky albedo (WSA) is retrieved. The results show that SegFormer outperforms the other two models for PV identification. From 2021 to 2025, the PV-covered area of the Talatan region expanded from 160.35 km² to 303.26 km². For the newly converted PV area, surface albedo decreased by 0.0391 and 0.0310 during 2021–2023 and 2023–2025, respectively, corresponding to local albedo-driven shortwave energy changes of 27.12 W·m⁻² and 23.55 W·m⁻². Consistent variation patterns are observed in the Xinjiang validation site. This study offers an integrated framework for characterizing PV expansion-induced land-cover changes and associated surface property variations, while providing an observation-based assessment of local shortwave energy variations related to surface albedo changes in arid regions. Full article

(This article belongs to the Special Issue Remote Sensing of Solar Radiation Absorbed by Land Surfaces (Second Edition))

► Show Figures

Figure 1

32 pages, 31387 KB

Open AccessArticle

Regional Marine Gravity Field Refinement by Integrating Region-Adaptive Fusion and Multi-Relational Graph Residual Learning

by Bing Liu, Houpu Li, Lin Wang, Libo Zhu, Houming Yang, Shaofeng Bian and Jingshu Li

Remote Sens. 2026, 18(18), 3182; https://doi.org/10.3390/rs18183182 - 16 Sep 2026

Abstract

Satellite-altimetry-derived marine gravity models often exhibit limited regional adaptability and region-dependent residual errors relative to shipborne observations, particularly in coastal, shelf, and slope areas. This study proposes a regional marine gravity refinement method that integrates region-adaptive background-field fusion with multi-relational graph neural network [...] Read more.

Satellite-altimetry-derived marine gravity models often exhibit limited regional adaptability and region-dependent residual errors relative to shipborne observations, particularly in coastal, shelf, and slope areas. This study proposes a regional marine gravity refinement method that integrates region-adaptive background-field fusion with multi-relational graph neural network residual learning in the northern South China Sea and adjacent waters. Four background models—SIO/UCSD, SDUST2022GRA, NSOAS24, and SWOT05—were used together with shipborne gravity, bathymetry, distance-to-coast, and survey-line information. A region-adaptive initial field was first constructed according to the error characteristics of the background models in different subregions, and its difference from the shipborne observations was taken as the residual-learning target. The matched shipborne points were then represented as graph nodes, with spatial, terrain, model-response, survey-line, and regional relations used to construct a multi-relational graph. Spatially disjoint blocks were used to separate the training, validation, and test samples. The Multi-relational GNN predicted local residuals, which were added back to the region-adaptive initial field to obtain the refined gravity anomalies. On the held-out test set, the proposed method achieved an RMSE of 6.10 mGal, an MAE of 3.83 mGal, a 95th-percentile absolute error of 13.08 mGal, a bias of −0.19 mGal, and a squared Pearson correlation coefficient r² of 0.945, outperforming the interpolation, machine-learning, and neural-network baselines. Ablation experiments showed that the survey-line relation provided the largest individual contribution. However, the present validation is limited to spatially held-out samples within the existing shipborne survey network; generalization to completely unseen cruises, other marine regions, and areas without nearby shipborne constraints remains to be further verified. Overall, the results indicate that combining regional background-model adaptation with structured residual learning can improve regional marine gravity field refinement in spatially heterogeneous environments. Full article

(This article belongs to the Special Issue Advancing Ocean Observation, Analysis, and Forecasting Through AI-Powered Remote Sensing)

► Show Figures

Figure 1

25 pages, 15338 KB

Open AccessArticle

A Canopy-Scale Fluorescence Approach for Evaluating Seasonal Photochemical Dynamics Across Different U.S. Forests

by Damilola Ajewole and Joseph D. White

Remote Sens. 2026, 18(18), 3181; https://doi.org/10.3390/rs18183181 - 16 Sep 2026

Abstract

Terrestrial ecosystems regulate atmospheric carbon exchange through photosynthesis while providing ecosystem services relevant to forest health, land management, and climate adaptation. Forests are particularly important because of their central role within global carbon cycling. Solar-induced fluorescence (SIF), which originates from chlorophyll fluorescence associated [...] Read more.

Terrestrial ecosystems regulate atmospheric carbon exchange through photosynthesis while providing ecosystem services relevant to forest health, land management, and climate adaptation. Forests are particularly important because of their central role within global carbon cycling. Solar-induced fluorescence (SIF), which originates from chlorophyll fluorescence associated with photosystem II (PSII), has become a valuable remote-sensing signal for monitoring vegetation activity across ecosystems. While laboratory fluorescence measurements are widely used to evaluate PSII function, efforts to translate comparable fluorescence-based concepts to satellite observations remain limited, particularly across different forests, phenology, and climatic conditions. Here, we analyze evergreen needleleaf, mixed, and deciduous forests across the United States using satellite-derived SIF observations developed from Orbiting Carbon Observatory-2 (OCO-2) retrievals. We derive a canopy-scale analog of PSII efficiency (

{Φ C}_{P S I I}

) from fluorescence yield (

Φ_{S I F}

) using observed minimum and maximum bounds within each observation period, following established relationships between steady-state fluorescence yield and PSII operating efficiency. We further estimate a canopy-scale electron transport rate (ETR_C) by integrating

{Φ C}_{P S I I}

with absorbed photosynthetically active radiation (APAR). Seasonal analyses showed clear temporal behaviors between and across forest types. While

Φ_{S I F}

exhibited consistent seasonal trajectories with relatively weak sensitivity to short-term atmospheric variability,

{Φ C}_{P S I I}

captured stronger seasonal shifts in relative photochemical behavior. Both

Φ S I F

and

{Φ C}_{P S I I}

showed weak or inconsistent relationships with gross primary productivity (GPP), indicating that both metrics alone do not fully represent canopy-scale carbon assimilation. APAR and derived ETR_C were positively related to GPP at all four sites. However, ETR_C explained more variation than APAR only at the mixed and deciduous sites, whereas APAR performed better at the evergreen needleleaf sites. These findings indicate that much of the ETR_C–GPP relationship was attributable to absorbed radiation, while the additional contribution of PSII was site-dependent. Thus, combining absorbed radiation with derived canopy-scale PSII efficiency may provide additional information about photosynthetic activity under some canopy conditions, but it does not consistently improve upon APAR alone. Full article

(This article belongs to the Section Forest Remote Sensing)

► Show Figures

Figure 1

36 pages, 16028 KB

Open AccessReview

Red-Edge Information in Agricultural Remote Sensing: From Spectral Theory to Explainable Machine Learning

by Ignacio Fuentes, Nikolas Hoskin, Patrick Filippi, Abhash Joshi, Yi Yu, Thomas F. A. Bishop and Dhahi Al-Shammari

Remote Sens. 2026, 18(18), 3180; https://doi.org/10.3390/rs18183180 - 16 Sep 2026

Abstract

The red-edge (RE) spectral region has become a central component of agricultural remote sensing because it captures physiologically meaningful changes in chlorophyll content, canopy structure and vegetation functioning. The availability of dedicated RE bands on modern multispectral satellites and advances in hyperspectral sensing [...] Read more.

The red-edge (RE) spectral region has become a central component of agricultural remote sensing because it captures physiologically meaningful changes in chlorophyll content, canopy structure and vegetation functioning. The availability of dedicated RE bands on modern multispectral satellites and advances in hyperspectral sensing have stimulated widespread applications for crop monitoring, nutrient assessment, stress detection and yield prediction. However, reported improvements over conventional visible–near-infrared (VIS–NIR) approaches remain highly variable, and the mechanisms governing when and why RE information provides additional value are often poorly synthesised. This review presents a conceptual framework that links the physical and physiological basis of RE reflectance with its condition-dependent agronomic performance and its emerging role within modern machine learning (ML) systems. We first examine how pigment absorption, canopy structure and sensor characteristics jointly determine the representation of RE information from hyperspectral measurements to operational multispectral observations. We then synthesise evidence demonstrating that the agronomic value of RE information is strongly dependent on crop characteristics, phenological stage, environmental conditions and observation geometry, explaining much of the variability reported across previous studies. Finally, we show how recent advances in ML and explainable artificial intelligence have changed the interpretation of RE information. Rather than evaluating RE-derived vegetation indices in isolation, contemporary predictive frameworks integrate RE observations with complementary spectral, climatic, structural and temporal predictors, allowing their physiological contribution to be quantified within multidimensional models. We conclude that future value of RE remote sensing will require not only continued advances in spectral measurement and vegetation index development, but also improved interpretation, transferability and operational integration of physiologically meaningful RE information within explainable, multi-source agricultural monitoring systems. Full article

(This article belongs to the Special Issue Advanced Remote Sensing Techniques in Agriculture and Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 7202 KB

Open AccessArticle

Gas Plume Detection from Infrared Hyperspectral Remote Sensing Data Based on Deep Learning Algorithms

by Suyi Wu, Chengyu Liu, Jidai Chen and Jiasong Shi

Remote Sens. 2026, 18(18), 3179; https://doi.org/10.3390/rs18183179 - 16 Sep 2026

Abstract

Infrared hyperspectral remote sensing is effective for chemical gas detection because gas molecules exhibit characteristic absorption features in the mid- and long-wave infrared region. This study considers coexisting gas components along a common line of sight rather than geometrically distinct spatial plumes. We [...] Read more.

Infrared hyperspectral remote sensing is effective for chemical gas detection because gas molecules exhibit characteristic absorption features in the mid- and long-wave infrared region. This study considers coexisting gas components along a common line of sight rather than geometrically distinct spatial plumes. We propose a compact spectral one-dimensional convolutional neural network (1D-CNN) for pixelwise gas species identification and the extraction of binary detection regions directly from 121-band spectra. Across five independently simulated NETD conditions and cross-noise train–test evaluations, the model maintained consistently strong classification performance over the examined noise range. On the measured scenes, the proposed model was compared with four traditional detectors and an adapted spectral Transformer baseline, showing a favorable and comparatively consistent Precision–Recall balance across the four target gases. These results support a fixed-platform field proof of concept, but do not constitute airborne-platform, edge deployment, quantitative concentration retrieval, or broad cross-site validation. Full article

(This article belongs to the Special Issue Research on Infrared Hyperspectral Remote Sensing Images)

► Show Figures

Figure 1

38 pages, 47645 KB

Open AccessReview

Dynamic Reconstruction of Vegetation Earth Observation Time Series: Beyond Gap-Filling in Level-3 Products

by Jochem Verrelst

Remote Sens. 2026, 18(18), 3178; https://doi.org/10.3390/rs18183178 - 16 Sep 2026

Abstract

Level-3 (L3) Earth observation (EO) products are commonly generated through temporal compositing, smoothing, and gap-filling of Level-2 retrievals. While these procedures provide spatially and temporally continuous datasets, they rely on interpolation assumptions that cannot adequately capture high-frequency, non-linear physiological dynamics of vegetation. As [...] Read more.

Level-3 (L3) Earth observation (EO) products are commonly generated through temporal compositing, smoothing, and gap-filling of Level-2 retrievals. While these procedures provide spatially and temporally continuous datasets, they rely on interpolation assumptions that cannot adequately capture high-frequency, non-linear physiological dynamics of vegetation. As a result, reconstructed time series often exhibit attenuated variability, temporal lag, and aliasing, with limited consistency with underlying ecosystem processes. This review proposes a shift from conventional gap-filling toward dynamic reconstruction, in which L3 products are interpreted as inferred trajectories of observable vegetation variables conditioned on sparse observations, complementary information, and explicit constraints. Dynamic reconstruction integrates satellite observations with complementary information, including multi-sensor EO data, meteorological drivers, spatial context, and model-based priors. The review critically synthesizes the principal methodological families for dynamic reconstruction and examines how complementary information and explicit constraints improve the reconstruction of vegetation dynamics while introducing trade-offs in uncertainty representation, physical consistency, scalability, and scale compatibility. Examples spanning physiological, environmental, and event-driven regimes illustrate how conventional L3 processing is particularly challenged by highly dynamic variables such as solar-induced chlorophyll fluorescence, evapotranspiration, land surface temperature, and stress indicators. These variables remain undersampled by satellite observations, leading to loss of short-term variability and distorted timing of rapid responses. Dynamic reconstruction provides a unifying framework for improving the representation of vegetation dynamics by explicitly accounting for observability, uncertainty, and cross-scale consistency. Overall, for highly dynamic vegetation variables, L3 products are increasingly understood as reconstructed trajectories rather than merely as gap-filled observations. This perspective may enhance the reliability and interpretability of EO-based monitoring of vegetation function and stress in an era of increasingly frequent, multi-sensor observations. Full article

(This article belongs to the Special Issue Remote Sensing for Vegetation Biophysical and Biochemical Parameters Retrieval)

► Show Figures

Figure 1

28 pages, 85049 KB

Open AccessArticle

Spatially Constrained Grassland Aboveground Biomass Estimation by Identifying and Masking Achnatherum splendens: Integrating UAV Remote Sensing and Deep Learning

by Yuxuan Zhang, Xiaojun Yao and Juan Zhang

Remote Sens. 2026, 18(18), 3177; https://doi.org/10.3390/rs18183177 - 16 Sep 2026

Abstract

Accurate estimation of forage aboveground biomass (AGB) from unmanned aerial vehicle (UAV) imagery is essential for monitoring alpine grassland productivity and supporting sustainable grassland management. However, the biomass of non-palatable species may be included in remote sensing-based estimates when their spatial distribution is [...] Read more.

Accurate estimation of forage aboveground biomass (AGB) from unmanned aerial vehicle (UAV) imagery is essential for monitoring alpine grassland productivity and supporting sustainable grassland management. However, the biomass of non-palatable species may be included in remote sensing-based estimates when their spatial distribution is not explicitly considered, potentially affecting spatial assessments of forage biomass. This study developed a UAV RGB-based framework for spatially constrained grassland AGB assessment by integrating the extraction of the growing-season non-palatable species Achnatherum splendens, mask-based spatial exclusion, feature optimization, and AGB inversion using field measurements from the northwestern shore of Qinghai Lake. Among tested semantic segmentation models, the Attention U-Net achieved the highest segmentation accuracy and was selected to identify A. splendens, while vegetation indices (VIs) and gray-level co-occurrence matrix (GLCM) texture features were optimized using the minimum redundancy maximum relevance (mRMR) algorithm. Random forest regression (RFR), support vector regression (SVR), and partial least squares regression (PLSR) models were subsequently evaluated. The Attention U-Net achieved high segmentation accuracy (PA = 89.98%, mIoU = 88.89%, and F1 = 93.88%). Feature optimization improved the performance of all regression models, with SVR providing the highest estimation accuracy (R² = 0.72; RMSE = 23.73 g m⁻²). The estimated AGB ranged from 67.88 to 205.85 g m⁻², revealing pronounced spatial heterogeneity. In a typical sample area with high-density A. splendens, excluding pixels classified as A. splendens reduced the estimated AGB by 15.45%, demonstrating the influence of dense A. splendens patches on spatial AGB assessment. These results demonstrate that integrating deep learning-based species masking with feature optimization provides a spatially explicit approach for grassland AGB assessment after excluding areas classified as A. splendens and provides useful spatial information for fine-scale grassland monitoring and management. Full article

(This article belongs to the Special Issue Multi-Source Remote Sensing for Terrestrial Vegetation and Ecosystem Services Mapping)

► Show Figures

Figure 1

26 pages, 34135 KB

Open AccessArticle

Comparative Multi-Data and Multi-Method InSAR for Deformation Monitoring and Visualization: A Case Study of Baode, China

by Zhen Tian, Yuedong Wang, Wenfu Yang, Jiakang Chen, Weibing Li, Jinyuan Liu and Bin Wang

Remote Sens. 2026, 18(18), 3176; https://doi.org/10.3390/rs18183176 - 15 Sep 2026

Abstract

It remains unclear why deformation results obtained by applying different MT-InSAR methods to the same dataset, as well as those from different SAR datasets, exhibit discrepancies. Hence, this study selects Baode County, located in the Loess Plateau, as the study area to conduct [...] Read more.

It remains unclear why deformation results obtained by applying different MT-InSAR methods to the same dataset, as well as those from different SAR datasets, exhibit discrepancies. Hence, this study selects Baode County, located in the Loess Plateau, as the study area to conduct a comparative analysis of multi-source SAR data and multiple MT-InSAR techniques for surface deformation monitoring. The datasets consist of concurrent Radarsat-2 and Sentinel-1 images acquired from October 2020 to June 2024. PS-InSAR, SBAS-InSAR, and IPTA-InSAR are adopted to compare their applicability across multiple dimensions, such as point coverage, deformation correlation, and mapping performance. Furthermore, based on IPTA-InSAR, the influences of spatiotemporal resolutions from different datasets on monitoring results are analyzed. The Sequential Turning Point Detection (STPD) method is incorporated to characterize the dynamic evolution of deformation and its correlation with precipitation. The results indicate that the three techniques exhibit favorable consistency and complementarity across diverse landform types. Nevertheless, SBAS-InSAR’s superiority in point density cannot be translated into an ability to represent continuous deformation fields. In contrast, IPTA-InSAR demonstrates better adaptability to complex surface conditions. Regarding data sources, Radarsat-2 achieves superior monitoring performance thanks to its high spatial resolution, yet its monitoring capacity is sensitive to variations in spatial resolution. Multi-looking not only reduces the maximum subsidence rate by approximately half but also increases elevation uncertainty by up to 24.8% and deformation-rate uncertainty by up to 42.1%. Sentinel-1, with its shorter revisit cycle, provides temporal sampling advantages that significantly enhance the ability to capture rapid subsidence signals. Through controlled-variable experiments, a dual-comparison analysis of multi-source SAR datasets and multiple MT-InSAR techniques enables the separation of discrepancies induced by algorithms from those originating in the datasets. The multifaceted experimental design provides a relatively comprehensive assessment of the influencing factors. The findings of this study can serve as references for InSAR data source combinations, technique selection, results presentation, and reliability assessment of deformation results in complex monitoring areas. Full article

(This article belongs to the Section Environmental Remote Sensing)

21 pages, 4277 KB

Open AccessArticle

Boundary-Guided Dual-Perspective Cross-Modal Fusion Network for RGB-IR Object Detection

by Huachen Lin, Zhiwei Fu, Xiumei Chen and Guirong Feng

Remote Sens. 2026, 18(18), 3175; https://doi.org/10.3390/rs18183175 - 15 Sep 2026

Abstract

Visible-infrared (RGB-IR) object detection leverages multimodal information to ensure reliable perception in complex environments. However, dynamic scenes pose significant challenges due to the frequent inconsistency between scene-level modality contributions and local spatial reliability. Furthermore, standard feature extraction progressively attenuates boundary-sensitive structural cues, and [...] Read more.

Visible-infrared (RGB-IR) object detection leverages multimodal information to ensure reliable perception in complex environments. However, dynamic scenes pose significant challenges due to the frequent inconsistency between scene-level modality contributions and local spatial reliability. Furthermore, standard feature extraction progressively attenuates boundary-sensitive structural cues, and unified fusion strategies often fail to capture spatially varying cross-modal complementarity. To overcome these limitations, we propose a Boundary-Guided Dual-Perspective Cross-Modal Fusion Network (BDPNet) to explicitly preserve shallow geometric structures and decouple deep semantic fusion into macroscopic and microscopic perspectives. Specifically, a Geometric Boundary Enhancement Module (GBEM) embeds Sobel-based high-frequency priors into shallow dual-modal features via residual spatial modulation, preventing the loss of crucial localization cues during downsampling. In the deep semantic space, a Hybrid Dual-Perspective Adaptive Fusion Module (HDAM) employs an illumination-aware branch for global modality weighting and a spatial confidence-driven branch for local cross-modal rectification. A spatial gating mechanism then dynamically reconciles these macro-environmental and micro-signal features. Extensive experiments on M3FD, LLVIP, and DroneVehicle demonstrate the effectiveness of BDPNet. Compared with state-of-the-art methods, BDPNet improves mAP

_{50 - 95}

by 0.8% and 1.0% on M3FD and LLVIP, respectively, and improves mAP

_{50}

by 0.6% on DroneVehicle, while using substantially fewer parameters and lower computational cost. Full article

(This article belongs to the Section AI Remote Sensing)

20 pages, 14629 KB

Open AccessArticle

Seafloor Topography Prediction from Altimetry-Derived Gravity Data Using a Wavelet-Assisted and High-Frequency Enhancement Neural Network

by Shuai Wang, Shaofeng Bian, Guojun Zhai and Nengfang Chao

Remote Sens. 2026, 18(18), 3174; https://doi.org/10.3390/rs18183174 - 15 Sep 2026

Abstract

Seafloor topography (ST) has important significance for earth science research, marine resource exploration and underwater navigation. The conventional ST inversion methods are limited by linear approximation and poor small-scale topographic feature prediction. This study proposes a novel Wavelet-Assisted and High-Frequency Enhancement Neural Network [...] Read more.

Seafloor topography (ST) has important significance for earth science research, marine resource exploration and underwater navigation. The conventional ST inversion methods are limited by linear approximation and poor small-scale topographic feature prediction. This study proposes a novel Wavelet-Assisted and High-Frequency Enhancement Neural Network (WAHFENN), an architecture integrating discrete wavelet transform (DWT), low-frequency retainment module (LFRM) and high-frequency enhancement module (HFEM) to enhance bathymetry prediction accuracy and capture small-scale topographic features. We apply the WAHFENN to predict the ST in a local area of the South China Sea (SCS). The results demonstrate that the WAHFENN model achieves a standard deviation (STD) of 50.66 m against shipborne single-beam check points, outperforming the topo_27.1 and SDUST2023BCO models by 31.46% and 28.49%, and surpassing the conventional Smith and Sandwell (SAS) method, gravity-geological method (GGM), and convolutional neural network (CNN) method by 78.23 m, 65.18 m, and 4.4 m, respectively. The WAHFENN model achieves a STD of 103.80 m against shipborne multibeam bathymetry data, representing improvements of 38.75%, 25.16%, and 15.58% over the SAS, GGM, and CNN models, respectively. The topographic detail comparisons and power spectral density analysis demonstrate that the WAHFENN model has the potential to outperform conventional methods in identifying small-scale topographic features. Full article

(This article belongs to the Special Issue Remote Sensing in Space Geodesy and Cartography Methods (Fourth Edition))

Journal Description

Remote Sensing

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI