International journal of applied earth observation and geoinformation : ITC journal最新文献

{"title":"DATerra: Boundary and structure aware domain adaptation for cross-regional terraced parcel extraction","authors":"Zhiwei Zhang,&nbsp;Xingyuan Zeng,&nbsp;Xinkai Kong,&nbsp;Juepeng Zheng,&nbsp;Haoyuan Liang,&nbsp;Guowei Zhou,&nbsp;Bohan Shi,&nbsp;Lingyuan Zhao,&nbsp;Jianxi Huang,&nbsp;Haohuan Fu","doi":"10.1016/j.jag.2026.105579","DOIUrl":"10.1016/j.jag.2026.105579","url":null,"abstract":"<div><div>Irregular agricultural parcels, particularly terraced fields, exhibit complex geometries and fine-scale boundaries that are highly sensitive to cross-regional variations in imaging conditions and landscape patterns. Although unsupervised domain adaptation (UDA) has shown promise for remote sensing segmentation under domain shifts, most existing methods primarily focus on semantic alignment while failing to adequately preserve boundary geometry and parcel-level structural consistency, often leading to boundary adhesion and distorted parcel delineation in target domains. To address these limitations, we propose DATerra, a boundary and structure aware domain adaptation framework for cross-regional terraced parcel extraction. The framework couples two architecture-level boundary-modeling modules with two training-level structure-preserving strategies: (i) Boundary-Guided Attention Fusion (BGAF), which injects geometry-aware cues into multi-scale feature learning; (ii) Boundary-aware Uncertainty-guided Gating (BUDG), which selectively refines ambiguous boundary regions while preserving reliable parcel interiors; and (iii) Parcel Structural Consistency (PSC), together with Structure-Aware ClassMix (SA-ClassMix), which promotes stable parcel predictions under partial target-domain observations and preserves parcel–boundary structural units during cross-domain mixing. Extensive experiments on the GTPBD-China benchmark, covering four geographic regions and twelve cross-domain transfer scenarios, demonstrate that DATerra substantially improves boundary delineation and object-level parcel integrity. On average, DATerra improves OIS and ODS by 14.00 and 10.76 percentage points, respectively, while reducing GUC and GTC by 20.14 and 9.98 points compared with the runner-up methods. Pixel-level metrics are also consistently improved, with an average gain of 1.23%. These results highlight the importance of explicitly modeling boundary geometry and structural consistency for robust cross-regional terraced parcel extraction.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105579"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148980352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-frequency microwave remote sensing reveals stratified forest responses to diverse drought stresses","authors":"Xu Zhang,&nbsp;Xiang Zhang,&nbsp;Fei Zhang,&nbsp;Xihui Gu,&nbsp;Hongliang Ma,&nbsp;Aminjon Gulakhmadov,&nbsp;Rabindra Kumar Panda,&nbsp;Mahlatse Kganyago,&nbsp;Veber Costa,&nbsp;Won-Ho Nam,&nbsp;Dash Subhaprada,&nbsp;Uma Charan Mohanty,&nbsp;Jiangyuan Zeng,&nbsp;Wen Xiao,&nbsp;José A. Marengo,&nbsp;Chao Yang,&nbsp;Wenying Du,&nbsp;Zeqiang Chen,&nbsp;Longgang Xiang,&nbsp;Nengcheng Chen","doi":"10.1016/j.jag.2026.105545","DOIUrl":"10.1016/j.jag.2026.105545","url":null,"abstract":"<div><div>Under climate change, increasing frequency and intensity of droughts pose severe threats to forest water dynamics and ecosystem stability. However, layer-specific responses to drought and their global spatial patterns remain insufficiently explored. This study utilized multi-frequency vegetation optical depth (VOD) datasets (X-, C-, and L-bands) that are sensitive to canopy, sub-canopy, and woody tissue moisture, to explore stratified forest responses at the global scale. A drought-induced relative anomaly index (ΔVOD%) was integrated with the standardized precipitation evapotranspiration index to characterize moisture dynamics under different drought types. Vertically, the canopy exhibited the strongest response intensity (mean ΔVOD% in the X-band = 44.5 % ± 20.9 %), whereas the woody tissue layer showed weaker but more delayed and persistent responses (mean lag = 2.56 and 2.44 months, respectively). A clear vertical gradient was identified: response intensity decreased from the canopy to the woody tissue layer, whereas lag and duration increased. Spatially, stronger canopy and sub-canopy responses were concentrated in evergreen broadleaf forests and tropical-temperate regions, while woody tissue responses were more pronounced in savannas and cold regions. Evergreen needleleaf, deciduous broadleaf, mixed forests, and arid zones exhibited clear inter-layer differences in response lag, whereas others showed relatively small variations. By leveraging the penetration capability of microwave remote sensing, we elucidated global patterns of layer-specific response intensity, lag, and duration and examines the effects of drought type, forest type, and climate zone on moisture dynamics. These findings provide new insights into global forest water responses under drought stress and improve remote sensing-based monitoring of forest drought impacts.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105545"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148895339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A directional feature excavation transformer for oriented detection of small-scale ships in dense SAR imagery","authors":"Junjie Zhang,&nbsp;Baoxiang Huang,&nbsp;He Gao,&nbsp;Borui Li,&nbsp;Ge Chen","doi":"10.1016/j.jag.2026.105569","DOIUrl":"10.1016/j.jag.2026.105569","url":null,"abstract":"<div><div>The precise oriented detection of dense and small-scale ships within Synthetic Aperture Radar (SAR) imagery constitutes a significant challenge for automated maritime surveillance systems because of intense clutter, minimal target sizes, and arbitrary rotations. To address these challenges, this paper proposes a coordinated multi-stage feature refinement framework, termed DiFE-TransOBB, tailored for dense SAR ship detection. Rather than relying on isolated module enhancements, the proposed architecture establishes a progressive interaction mechanism across structural, spatial, and frequency domains. Specifically, the Directional Feature Excavator (DiFE) module can extract geometry-aware structural priors to suppress isotropic clutter interference, the High-Resolution Spatial Fidelity Preservation Branch (HSFPB) preserves fine-grained localization details of tiny ships, and the Dual-Domain Interaction Fusion (DualFusion) performs conditional frequency-domain refinement guided by these spatial-structural cues to disentangle ship contours from unstructured high-frequency sea clutter. Evaluated on the newly constructed DenseSARShip-v1 benchmark and further validated on public datasets, DiFE-TransOBB achieved the highest detection performance among the evaluated methods while maintaining a favorable accuracy–efficiency trade-off. These results demonstrate the effectiveness and cross-dataset generalization capability of the proposed framework for oriented ship detection in dense and cluttered SAR scenes.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105569"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148936101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Resolution-dependent divergence of optimal segmentation scale across land-cover types in a coastal wetland landscape: A systematic empirical characterization from 0.02 to 30 m near the Yellow River estuary, Dongying, China","authors":"Xiaonan Zhou,&nbsp;Junkai Shi,&nbsp;Qingyu Li,&nbsp;Zhenguo Niu","doi":"10.1016/j.jag.2026.105558","DOIUrl":"10.1016/j.jag.2026.105558","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Optimal segmentation scale is a core parameter in object-based image analysis (OBIA). However, its variation with spatial resolution and land-cover type remains insufficiently characterized, constraining cross-resolution scale transfer in multi-source remote sensing mapping workflows. Using a coastal wetland landscape near the Yellow River estuary in Dongying, China, as the study area, this study systematically characterized optimal segmentation scales for seven land-cover types—tidal flat, bare land, buildings, water bodies, roads, cropland, and vegetation—across six spatial-resolution levels from 0.02 to 30 m. The optimal scale of each land-cover type was extracted using the Ratio of Mean Difference to Neighbors (absolute) to Standard Deviation (RMAS) method. Local variance (LV) quantified spatial heterogeneity, and perimeter-area fractal dimension (PAFRAC) provided an auxiliary descriptor of boundary complexity. Empirical regression models relating optimal scale to spatial resolution and LV were developed, and their utility was evaluated through classification and search-efficiency analyses.&lt;/div&gt;&lt;div&gt;The results show that: (1) at the same spatial resolution, land-cover types with lower LV, namely tidal flat and water bodies, were consistently associated with larger optimal segmentation scales, whereas land-cover types with higher LV, namely buildings and roads, were associated with smaller optimal segmentation scales, indicating a stable negative cross-sectional correspondence. The PAFRAC results provided auxiliary support for this correspondence from the perspective of boundary complexity. (2) The functional form of the resolution–scale response systematically diverged by land-cover type: tidal flat and water bodies followed exponential-function models (R&lt;sup&gt;2&lt;/sup&gt; = 0.985–0.994), whereas bare land, buildings, vegetation, roads, and cropland followed power-function models (R&lt;sup&gt;2&lt;/sup&gt; = 0.931–0.996). This difference in function type was also reproduced in the LV–scale model, showing a consistent empirical pattern across the two model formulations. (3) In the 0.02 m ultra-high-resolution unmanned aerial vehicle (UAV) imagery, scale reversal was observed for buildings and vegetation: their optimal segmentation scales were lower than the corresponding values at 0.5 m and 2 m, deviating from the monotonic trend over the 0.5–30 m range. This phenomenon may reflect a shift in the dominant source of spatial heterogeneity from macroscopic patch morphology to micro-scale internal texture; however, because of the limited coverage of the UAV data, this interpretation requires further verification. (4) Across the five full-area satellite-image resolutions, overall accuracy (OA) varied non-monotonically with spatial resolution. The 10 m imagery achieved the highest OA (OA = 97.85%, Kappa = 0.97). Tidal flat and water bodies showed stable accuracy across the five satellite-image resolutions, whereas the accuracies of buildings and roads decr","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105558"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148884166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Three decades of Antarctic Ice Sheet surface melt dynamics with disentangled radiative and turbulent controls","authors":"Ziqian Zhang,&nbsp;Wanchun Leng,&nbsp;Lei Zheng,&nbsp;Xiao Cheng,&nbsp;Tianjie Zhao,&nbsp;Teng Li,&nbsp;Qi Liang,&nbsp;Mengxi Zhai,&nbsp;Lingmei Jiang","doi":"10.1016/j.jag.2026.105578","DOIUrl":"10.1016/j.jag.2026.105578","url":null,"abstract":"<div><div>Surface melt over the Antarctic Ice Sheet (AIS) is a critical precursor to ice shelf instability and dynamic mass loss, yet its fine-scale spatiotemporal variability and underlying physical drivers remain poorly constrained. Existing surface melt products (12.5–25 km) obscure melt dynamics in topographically complex coastal zones. Here, we generated a novel 3.125 km daily surface melt record (1992–2023) by implementing a Fisher Discriminant Analysis (FDA) approach on enhanced-resolution passive microwave inputs. Validated against automatic weather station data, the FDA approach achieved &gt; 96% overall accuracy, successfully resolving intricate melt patterns along narrow fjords and grounding lines. Trend analysis reveals divergent evolution: Antarctic Peninsula (AP) melt duration has stabilized since 2000, whereas significant localized melt intensification occurred along East Antarctic ice shelf margins. To explain these regional disparities, by integrating this high-resolution record with RACMO2.4p1 energy fluxes using Lindeman-Merenda-Gold (LMG) variance decomposition, we quantified the drivers of interannual melt variability. By evaluating the relative dominance of radiative versus turbulent fluxes, we classify Antarctic ice shelves into three sensitivity regimes: (1) Radiation-controlled regime (e.g., Ross, Shackleton) dominated by shortwave radiation and albedo feedbacks; (2) Turbulence-driven regime (e.g., Mertz, Getz) where sensible and latent heat fluxes drive melt through dynamic atmospheric forcing; and (3) Mixed-control regime (e.g., Larsen C, Amery) governed by a complex interplay of both processes. These findings highlight the specific vulnerability of turbulence-sensitive sectors to atmospheric anomalies, providing a high-resolution, process-informed basis for assessing future ice shelf stability and mass loss projections.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105578"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148980353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond greenness: Combining MODIS vegetation trajectories and GEDI canopy structure to reveal contrasting structural states across the Hindu Kush Himalaya","authors":"Niti B. Mishra","doi":"10.1016/j.jag.2026.105586","DOIUrl":"10.1016/j.jag.2026.105586","url":null,"abstract":"<div><div>Satellite greening is often interpreted as vegetation recovery, productivity gain, or woody expansion, yet optical vegetation indices alone cannot show whether greening reflects low-stature vegetation, developing woody cover, mature forest, biomass accumulation or structurally simplified canopy. This ambiguity is especially important in mountain regions, where climate, snow, topography and disturbance vary sharply over short distances. This study combined MODIS Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) trajectories from 2001 to 2024 with contemporary 1-km estimates of canopy height, aboveground biomass density, and vertical structural complexity from the Global Ecosystem Dynamics Investigation (GEDI) to develop a spaceborne remote sensing framework to characterize the contemporary structural context of satellite-observed woody vegetation greening across the Hindu Kush Himalaya. Valid woody pixels were classified into six spectral–structural states representing low-stature greening, woody structural greening, complex or high-biomass greening, mature woody browning, stable vegetation with hidden structural complexity, and simplified green forest. The environmental and disturbance settings of these classes were then evaluated using snow, temperature, precipitation, moisture stress, topography, forest loss, fire frequency, and nighttime lights. Greening occurred across a wide structural range, from low-stature vegetation to tall, high-biomass, structurally complex forest. Complex or high-biomass greening was associated with relatively moist and precipitation-favorable environments, whereas mature woody browning occurred in structurally developed landscapes experiencing increasing thermal and moisture stress and elevated forest loss. Spectrally stable but structurally complex vegetation showed comparatively high disturbance signals, although this class was rare. Simplified green forest was concentrated in colder, snow-influenced, relatively dry, and topographically constrained areas with little recent forest loss or fire, suggesting environmental limitation rather than recent degradation. Spatial process-context models distinguished the major classes with cross-validated ROC AUC values of 0.739–0.893. These results show that similar greenness trajectories can represent markedly different canopy conditions. Contemporary lidar structure therefore provides essential context for interpreting long-term optical trends, although it does not directly measure structural change over the full 2001–2024 period. The framework offers a more ecologically informative approach for evaluating mountain vegetation change than greenness trends alone.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105586"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148980354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SRAIN: An isolated-neighborhood-based framework for LST-based surface thermal anomaly extraction","authors":"Pengcheng Wu,&nbsp;Qingyan Meng,&nbsp;Linlin Zhang,&nbsp;Mona Allam,&nbsp;Longfei Liu,&nbsp;Hantian Wu","doi":"10.1016/j.jag.2026.105542","DOIUrl":"10.1016/j.jag.2026.105542","url":null,"abstract":"<div><div>LST-based surface thermal anomaly extraction is an important task in remote sensing data analysis and is widely used in disaster monitoring and environmental assessment. This study proposes an isolated-neighborhood-based surface thermal anomaly extraction framework, termed SRAIN, for extracting spatially localized LST-based surface thermal anomalies. Taking coal-fired power plants in China from 2013 to 2024 as the primary study object and using Landsat 8/9 land surface temperature (LST) data as input, each sample is represented by a 12-month LST feature vector to characterize intra-annual monthly thermal-state variations. Drawing upon Tobler’s First and Second Laws of Geography, SRAIN assumes that spatial anomalies exhibit an “isolated” characteristic. Initial neighborhoods are constructed using Voronoi diagrams and dynamically merged using Jaccard and Silhouette coefficients to form integrated neighborhoods, thereby constituting isolated neighborhoods composed of both initial and integrated neighborhoods. In the anomaly extraction stage, ten anomaly detection algorithms are integrated, a confidence–intensity hybrid anomaly score (<em>G-score</em>) is proposed, and adaptive threshold optimization is performed using a beam-search-inspired strategy. In the anomaly pattern analysis stage, detected anomalies are classified into three modes: Concentrated (63.39%), Stretched (33.04%), and Diffuse (3.57%). Under the proxy-label-based relative evaluation framework, SRAIN improves proxy-label-based relative performance and spatial autocorrelation for LST-based surface thermal anomalies in the coal-fired power plant scenario. Compared with the best single algorithm, the fused <em>G-score</em> reduces the proxy-label-based misclassification rate by 12.9% and increases the spatial autocorrelation coefficient by 10.8%. In addition, the earthquake and fire cases provided in the Supplementary Materials preliminarily illustrate the potential transferability of the framework to other LST-based surface thermal anomaly scenarios, although systematic cross-scenario validation remains necessary in future studies. Overall, SRAIN provides a transferable framework for complex LST-based surface thermal anomaly extraction and offers a new perspective for environmental monitoring of anthropogenic heat sources such as coal power plants.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105542"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148884237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling regional coseismic landslide intensity with an interpretable Log-Gaussian GAM: Integrating size, mobility, and their interactions","authors":"Binghai Gao,&nbsp;Yi Wang,&nbsp;Xiaolong Zhang,&nbsp;Xin Wang,&nbsp;Jingqi Huang,&nbsp;Pan Cao,&nbsp;Yongheng Li,&nbsp;Jiwei Wang","doi":"10.1016/j.jag.2026.105563","DOIUrl":"10.1016/j.jag.2026.105563","url":null,"abstract":"<div><div>Traditional regional landslide hazard assessments primarily focus on static susceptibility, often overlooking critical post-failure kinematic characteristics and their destructive potential. To address this gap, this study proposes a landslide intensity assessment framework integrating both landslide size and mobility characteristics, using the Ms6.8 Luding earthquake (2022) as a representative case. We developed intensity indices to reflect destructive potential across three dimensions: cumulative effects of all landslides within a slope unit, average landslide intensity, and maximum single-event intensity. An interpretable log-Gaussian Generalized Additive Model was employed for regional modeling, while the synergistic effects of potential controlling factors were systematically quantified. Results demonstrate that the proposed indices effectively capture multiple dimensions of destructive potential of regional landslide intensity. Under spatial cross-validation, the models showed satisfactory predictive performance and robustness, with predictions closely matching observations. Notably, the total effect model achieved Pearson’s correlation coefficient (R) of 0.809, Nash-Sutcliffe efficiency coefficient (NSE) of 0.648. Particularly, this study is the first to explicitly quantify nonlinear interactions among key controls (e.g., slope, seismic motion, fault), revealing their important contributions to landslide intensity assessment. By expanding the paradigm from occurrence probability to destructive intensity modeling, this study further complements and refines the existing landslide hazard assessment framework. The proposed framework provides a robust, interpretable tool for identifying high-risk zones, facilitating more effective disaster mitigation and emergency planning in seismically active regions.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105563"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148895348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PLGCA-SAM: Progressive local and global context-aware network incorporating SAM for remote sensing crop mapping","authors":"Lihua Cui,&nbsp;Wenting Han,&nbsp;Xuedong Zhai,&nbsp;Guang Li,&nbsp;Shah Jahan Leghari,&nbsp;Yi Liao,&nbsp;Ziao Zhou,&nbsp;Shenjin Huang","doi":"10.1016/j.jag.2026.105548","DOIUrl":"10.1016/j.jag.2026.105548","url":null,"abstract":"<div><div>Precise crop mapping via remote sensing is critical for the rational utilization of cultivated land resources. Remote sensing techniques and deep learning-based semantic segmentation methods provide effective approaches to large-scale crop mapping. However, due to variations among remote sensing imaging systems, significant distributional shifts exist across different remote sensing datasets, which limit the generalizability of deep learning models. To address the issue, we propose a semantic segmentation network named PLGCA-SAM for crop mapping in remote sensing imagery. PLGCA-SAM integrates the contextual perception capability of PLGCA with the powerful generalization of SAM. Specifically, we introduce a task-adaptive encoding (TAE) module, which includes a SAM adapter to align SAM’s generic visual features with the PLGCA feature space, and a task-guided mechanism that refines the fused representation using a task-aware loss. This design enables more effective feature integration and improves adaptability across diverse remote sensing datasets. Experiments conducted on GF-2 and Sentinel-2 datasets demonstrate that PLGCA-SAM achieves 2.03% and 1.50% improvements in mIoU, respectively, over SOTA methods. Our code will be obtained by: <span><span>https://github.com/Hanhlab/PLGCA-SAM.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105548"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148895438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Utilizing thermal infrared spectroscopy data to map lithology and mineral alteration in geothermally active areas","authors":"Federico Rabuffi,&nbsp;Simon J. Hook,&nbsp;Massimo Musacchio,&nbsp;Malvina Silvestri,&nbsp;Kerry Cawse-Nicholson,&nbsp;Maria Fabrizia Buongiorno,&nbsp;Zoe Amie Pierrat","doi":"10.1016/j.jag.2026.105550","DOIUrl":"10.1016/j.jag.2026.105550","url":null,"abstract":"<div><div>Mapping hydrothermal alteration mineralogy is essential for characterizing active geothermal systems and identifying prospects for geothermal energy and mineral resource assessment. The potential of thermal infrared (TIR: 8 to 13 μm) imaging spectroscopy for geothermal mineral mapping remains largely under-explored. Here we present the first ever lithological and mineralogical maps of Parco Naturalistico delle Biancane (PNB), part of the Larderello geothermal field, derived from TIR imaging spectroscopy data collected by the Hyperspectral Thermal Emission Spectrometer (HyTES). TIR data provides simultaneous information on both surface composition and temperature, enabling the combined mapping of alteration mineralogy and thermal anomalies from a single dataset. The limited rock exposure and strong lithological and alteration heterogeneity make PNB a rigorous test environment. We mapped the dominant mineralogical assemblages associated with geothermal alteration at PNB, including clays, silicate and hydrothermal alteration assemblages. By integrating TIR-derived surface mineralogy with surface temperature, we demonstrate a spatial correlation, linking mineralogical alteration to geothermal activity. We also compare two independent mineral mapping approaches, the Mineral Identification and Characterization Algorithms (MICA), extended to the longwave infrared and the recently developed Surface Mineralogy code (SM-code), based on Multiple Endmember Spectral Mixture Analysis (MESMA), adapted for use with HyTES emissivity data. Simulation of laboratory emissivity spectra at the spectral resolution of the future spaceborne TIR missions, such as SBG/EAGLE-TIR, TRISHNA, and LSTM, reveals that SBG/EAGLE-TIR has the highest discriminative capability. These results establish a validated methodological and spectral reference framework for next-generation spaceborne TIR missions, advancing the use of TIR imaging spectroscopy for geothermal exploration and mineral resource assessment.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"153 ","pages":"Article 105550"},"PeriodicalIF":8.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148933343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}