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

{"title":"Coupled ground subsidence and rapid urbanization of the Red River delta region and the city of Hanoi, Vietnam, revealed through a Multi-Track InSAR analysis","authors":"Qing Zhao ,&nbsp;Yifei Zhang ,&nbsp;Antonio Pepe ,&nbsp;Pietro Mastro ,&nbsp;Taotao Zheng ,&nbsp;Tianliang Yang","doi":"10.1016/j.jag.2025.104886","DOIUrl":"10.1016/j.jag.2025.104886","url":null,"abstract":"<div><div>The region of the Red River Delta represents one of the most crucial economic zones of Vietnam, and its capital, the city of Hanoi, is in the heart of the delta. To satisfy the water demand for agricultural irrigation, urbanization, and industrialization, over-pumping groundwater-induced-ground subsidence has long hindered the region’s sustainable development. Existing studies do not systematically assess land subsidence with two-dimensional analysis in the RRD mega-city region. In this work, a comprehensive analysis relying on the exploitation of the interferometric SAR technologies and the use of multi-track SAR datasets acquired from the European Copernicus Sentinel-1 and TerraSAR-X has been carried out to generate and interpret the 2017–2024 dynamics of the RRD terrain deformations, by generating 2-D maps, along the vertical and horizontal directions, and ground deformation time series. As a result, the megacities Hanoi, Hai Duong, and Nam Dinh of the delta are found to be affected by significant subsidence. Specifically, we found that substantial subsidence occurred in the urban-suburban fringe of Hanoi (four districts: Ha Dong, Hoai Duc, Thanh Tri, and Dan Phuong). Experimental results confirm that the subsidence dominated the ground deformations, whereas the horizontal displacements of the terrain (i.e., along East-West) are almost negligible. Our study also comprehensively analyses the relationships between population, land-cover changes, the distribution of built-up areas, the role of over-pumping groundwater, geological setting, and ground subsidence, revealing that geological setting and groundwater pumping are dominant factors of the observed ground subsidence bowls.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104886"},"PeriodicalIF":8.6,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated high-resolution 3D crevasse extraction and dynamic linkages: an integrated UAV-LiDAR, photogrammetry, and C-TransUNet framework","authors":"Yunpeng Duan ,&nbsp;Kunpeng Wu ,&nbsp;Jun Zhou ,&nbsp;Xin Yang ,&nbsp;Daoxun Gao ,&nbsp;Shiyin Liu","doi":"10.1016/j.jag.2025.104881","DOIUrl":"10.1016/j.jag.2025.104881","url":null,"abstract":"<div><div>Glacier crevasses are critical indicators of ice dynamics and stability, yet their detailed monitoring is hindered by the limitations of traditional remote sensing. This study presents an innovative, integrated framework combining Unmanned Aerial Vehicle (UAV)-based LiDAR Scanning (UAV-LS), photogrammetry, and an optimized deep learning model, C-TransUNet, for automated, high-resolution, three-dimensional (3D) crevasse characterization. We conducted surveys at the terminus of the Yanong Glacier (YNG), Tibetan Plateau, acquiring centimeter-resolution orthophotos and LiDAR point clouds. The enhanced C-TransUNet model, featuring a local–global collaborative encoder and adaptive multi-scale feature fusion, significantly outperformed a suite of well-established and representative methods in crevasse extraction (mIOU = 88.04 %, F1-Score = 87.06 %) and demonstrated promising spatial transferability. A novel workflow integrating the deep learning results with UAV-LS point clouds enabled the systematic extraction of 3D crevasse geometry, including length, width, orientation, and unprecedented detail in depth (average 3.06 ± 3.91 m, max 26.69 m). Five distinct crevasse types were identified and meticulously mapped, revealing significant variations across different altitudinal zones. Furthermore, surface strain rates calculated from UAV-derived velocity data revealed preliminary quantitative links between crevasse patterns and underlying glacier dynamics. Our initial findings suggest that transitions between crevasse types correspond to changes in the local strain regime. This study establishes a powerful, automated framework for fine-scale, multi-dimensional crevasse analysis, offering a robust foundation for gaining crucial insights into glacier mechanics and stability in response to climate change.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104881"},"PeriodicalIF":8.6,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A lightweight Context-aware adaptive fusion network for automatic identification of active landslides","authors":"Xingmin Cai ,&nbsp;Chuang Song ,&nbsp;Zhenhong Li ,&nbsp;Yi Chen ,&nbsp;Bo Chen ,&nbsp;Jiantao Du ,&nbsp;Chen Yu ,&nbsp;Wu Zhu ,&nbsp;Jianbing Peng","doi":"10.1016/j.jag.2025.104882","DOIUrl":"10.1016/j.jag.2025.104882","url":null,"abstract":"<div><div>Timely identification of active landslides is critical for disaster early warning and risk management. Interferometric Synthetic Aperture Radar (InSAR) technology, which can capture subtle displacements of active landslides over large areas, has become a key tool for landslide identification. The development of deep learning provides new opportunities to improve InSAR-based landslide identification. However, existing approaches often struggle to balance identification accuracy and computational efficiency. In this study, we propose the Context-aware Adaptive Fusion Network (CAFNet), a lightweight encoder-decoder framework that optimizes multi-scale feature learning from color-mapped deformation. In the encoder, the Wavelet-based Down-sampling Block (WDB) is introduced to perform down-sampling while preserving fine-grained details. Additionally, we develop a Multi-branch Scale-aware Aggregation (MSA) module to adaptively select and integrate multi-scale features based on target characteristics, ensuring flexible feature alignment. The decoder employs an efficient Conv-based Up-sampling Block (CUB) to progressively restore spatial resolution while refining boundaries. Experimental results demonstrate that CAFNet outperforms existing deep learning models such as DeepLabV3+ and ResUNet, achieving 90.8 % precision and 83.3 % IoU at the pixel level, and 89.5 % correct detection and 7.3 % false alarm rate at the object level. Notably, CAFNet achieves these results a 20 × reduction in parameters and a 50 % decrease in computational costs, while maintaining robust generalization abilities. These findings highlight the potential of CAFNet for the establishment and periodic updating of active landslide inventories, which is essential for minimizing losses caused by landslide disasters.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104882"},"PeriodicalIF":8.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dual-stage wildfire risk analysis in South Korea: Susceptibility mapping from a decade of FIRMS data and 2025 burn area detection with multi-sensor classification","authors":"Wahyu Luqmanul Hakim ,&nbsp;Muhammad Fulki Fadhillah ,&nbsp;Sungjae Park ,&nbsp;Chang-Wook Lee","doi":"10.1016/j.jag.2025.104890","DOIUrl":"10.1016/j.jag.2025.104890","url":null,"abstract":"<div><div>Wildfire frequency and severity have escalated in South Korea, with the March 2025 event being the most destructive in its history. This study presents a dual-stage analytical framework that integrates deep learning to assess wildfire susceptibility and multi-sensor satellite classification to delineate burn areas. First, a nationwide wildfire susceptibility model was constructed using a decade of NASA FIRMS hotspot data (2014–2024) and 12 conditioning factors. Among the four tested deep learning models, SqueezeNet achieved the highest predictive performance, with an area under the curve (AUC) value of approximately 0.83 and minimal error metrics. Second, active burn areas from the 2025 wildfire were mapped by fusing Sentinel‑1 synthetic aperture radar (SAR), which includes amplitude and coherence change detection, and Sentinel‑2 spectral indices, enabling precise delineation of burn across five provinces. A support vector machine classifier yielded an overall accuracy of 97.5 % and a Kappa coefficient of 0.95. The susceptibility map, validated against the 2025 fire perimeters, achieved an AUC of 0.78, confirming the reliability of the proposed integrated framework. This approach provides a robust foundation for early warning systems and ecological risk assessments by combining multi-temporal fire patterns with validation against actual burn area.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104890"},"PeriodicalIF":8.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Strengthening or weakening? Multi-year quantification and comparison of urban green space cooling effects and their key 2D/3D drivers","authors":"Chaobin Yang ,&nbsp;Huaiqing Wang ,&nbsp;Zhibin Ren ,&nbsp;Weiqi Zhou","doi":"10.1016/j.jag.2025.104888","DOIUrl":"10.1016/j.jag.2025.104888","url":null,"abstract":"<div><div>The cooling effect generated by urban green space (UGS) plays a vital role in mitigating heat waves and enhancing citizen well-being. However, long-term studies examining the evolution of cooling effect alongside rapid urbanization-induced UGS changes remain scarce. Focusing on Beijing, China, this study quantifies the spatiotemporal changes in UGS cooling effects and identifies their key two-dimensional (2D) and three-dimensional (3D) drivers over nearly four decades (1985–2023). We innovatively proposed three distinct cooling intensity (CI) indicators for spatially explicit analysis and employed both stepwise regression analysis and machine learning models. Key findings include: (1) Beijing’s UGS coverage exhibited an overall slight decline, yet its spatial distribution became more balanced. The proportion of grids with UGS coverage below 20 % decreased significantly, from 8 % in 1985 to less than 1 % in 2023. (2) The perceived trend in cooling effect strength (strengthening vs. weakening) critically depended on the CI indicator used. The traditional CI (temperature difference between UGS and surroundings) showed a continuous decrease from 2.65 °C in 1985 to 1.83 °C in 2023. Conversely, regression model slopes indicated that a 10 % increase in UGS coverage yielded a stronger cooling effect in recent years, despite declining model R² values. Additionally, nearly 32 % of the study area exhibited an increase in outside CI of at least 0.5 °C, indicating a strengthening trend in the cooling effect. (3) Both statistical and machine learning analyses consistently identified the Normalized Difference Vegetation Index (NDVI) as the dominant driver, explaining over 50 % of CI variations. Landscape metrics and 3D UGS features contributed 38 % and 10 %, respectively. Combining all 2D and 3D characteristics explained over 70 % of CI variations, with NDVI, mean vegetation height, and aggregation index (AI) being the top three positively influential features.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104888"},"PeriodicalIF":8.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bridging the cloud gap: AHI/ATMS synergy through CNN feature fusion for all-weather SST retrieval","authors":"Donglin Fan ,&nbsp;Xin Yang ,&nbsp;Hongchang He ,&nbsp;Hongjie He ,&nbsp;Bolin Fu","doi":"10.1016/j.jag.2025.104887","DOIUrl":"10.1016/j.jag.2025.104887","url":null,"abstract":"<div><div>Infrared-based Sea Surface Temperature (SST) retrieval methods face persistent challenges from cloud-induced data gaps and accuracy degradation. This study bridges this critical limitation through multisensor satellite synergy, integrating geostationary Advanced Himawari Imager (AHI) with Advanced Technology Microwave Sounder (ATMS) data via a Convolutional Neural Network (CNN) for all weather SST retrieval. The CNN model adaptively extracts features from multi-band AHI/ATMS imagery, effectively predicting SST under varying cloud conditions. Evaluation results demonstrate a root mean square error (RMSE) of 2.07 °C, a mean absolute error (MAE) of 1.22 °C, and a coefficient of determination (R²) of 0.88 on the test dataset. Under the same CNN framework, unimodal retrievals from AHI and ATMS alone yield substantially lower performance (R² = 0.51, RMSE = 3.45 °C; and R² = 0.63, RMSE = 2.64 °C, respectively), confirming the complementary benefits of multisensor fusion. Comparisons with a Transformer-based model, the daily OSTIA product, and the official AHI SST product (clear-sky conditions) further indicate that the proposed CNN achieves the highest accuracy. Although RMSE exceeds 1 °C for certain cloud types, the method substantially mitigates cloud-induced data loss and provides a reliable, high-accuracy, all-weather SST retrieval strategy for satellite ocean remote sensing.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104887"},"PeriodicalIF":8.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated recognition of oil and gas production infrastructure using satellite imagery","authors":"Sonu Dileep ,&nbsp;Daniel J. Zimmerle ,&nbsp;Nathaniel Blanchard","doi":"10.1016/j.jag.2025.104859","DOIUrl":"10.1016/j.jag.2025.104859","url":null,"abstract":"<div><div>Recent studies have highlighted the need to identify oil and gas (O&amp;G) facilities to connect anonymous aerial or satellite emissions surveys to specific facilities in the production basin. This study proposes a novel deep learning architecture that processes high-resolution (30 cm GSD) 3-band, pansharpened, visible-spectrum (RGB) satellite imagery from Maxar to identify facility outlines and key on-site equipment. The architecture utilizes a dual-branch model paradigm that combines few convolutional layers and Adaptive Fourier Neural Operators (AFNO) within a Transformer-based structure. One branch focuses on detecting two major equipment types at the site, while the other branch identifies overall facility boundaries. Comparison to test data indicates our architecture achieves 93% accuracy for facility identification with as few as 260 positive training samples. Comparing resulting facility data to regulatory reporting indicates that satellite deep-learning–based detection identifies more facilities, with greater detail and specificity than current reporting programs. To implement widespread anonymous aerial or satellite sampling, this type of facility recognition is likely required to attribute emission detections to O&amp;G facilities.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104859"},"PeriodicalIF":8.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"S2BAVG: A global Sentinel-2 grid for burned area product validation","authors":"Jon Gonzalez-Ibarzabal ,&nbsp;Aitor Bastarrika ,&nbsp;Stephen V. Stehman ,&nbsp;Daniela Stroppiana ,&nbsp;Magí Franquesa","doi":"10.1016/j.jag.2025.104889","DOIUrl":"10.1016/j.jag.2025.104889","url":null,"abstract":"<div><div>Accurate burned area (BA) mapping is essential for assessing wildfire impacts on ecosystems and climate. While existing BA products derived from coarse-resolution sensors (e.g., MODIS) have primarily relied on Landsat-based validation protocols, the advent of higher-resolution products such as those from Sentinel-2 necessitates adapted validation methodologies to match their enhanced spatial detail. This study presents the Sentinel-2 Burned Area Validation Grid (S2BAVG); a global sampling framework designed to support BA validation using Sentinel-2 imagery. S2BAVG consists of 19,263 non-overlapping spatial units covering the global land surface, addressing limitations of previous grids by ensuring full orbital coverage and eliminating overlaps, thereby enabling consistent sampling and rigorous validation. Key attributes—including fire activity indicators and cloud-free image availability— facilitate the implementation of stratified sampling designs. Additionally, we provide an open-source framework to support the sampling process with customizable input parameters. The framework includes statistical inference tools to estimate accuracy metrics and their standard errors, ensuring rigorous BA product assessment. By leveraging Sentinel-2′s high spatial and temporal resolution, S2BAVG provides a flexible and standardized methodology for BA validation. The S2BAVG tile grid dataset and sampling framework (with an illustrative sampling design approach) are openly available at <span><span>https://github.com/magifranquesa/S2BAVG</span><svg><path></path></svg></span>, promoting reproducibility and enabling broader applications in fire science and Earth observation.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104889"},"PeriodicalIF":8.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A distinct type of heavy rainfall with large raindrops over extratropical regions revealed by 10 years of GPM spaceborne radar measurements","authors":"Jihoon Ryu ,&nbsp;Jaeyeon Lee ,&nbsp;Yalei You","doi":"10.1016/j.jag.2025.104879","DOIUrl":"10.1016/j.jag.2025.104879","url":null,"abstract":"<div><div>Large-drop heavy rainfall, defined as heavy rainfall (&gt;10 mm h⁻¹) with relatively large raindrop diameters and low number concentrations, has been known to occur mainly in continental deep convection based on previous ground-based studies. With spaceborne radar, global analysis of raindrop size has become possible, providing a unique opportunity to revisit this understanding. Using 10 years (2014–2023) of GPM Dual-frequency Precipitation Radar (DPR) observations, large-drop heavy rainfall events are classified into two types with a Gaussian Mixture Model based on storm height. The two resulting types—high storm height (HSH) and low storm height (LSH)—exhibit similar DSD characteristics but distinct structural and environmental properties in observations and reanalysis data. The HSH type is associated with continental deep convection under warm conditions favorable for collision–coalescence processes. In contrast, the LSH type features shallower storm structures in cold environments, with large drops likely formed by melting snow. Seasonal analyses show that HSH events occur mainly over continental regions in summer, whereas LSH events are mostly observed over midlatitude oceans in winter. For diurnal variation, HSH events exhibit a daytime peak, while LSH events show no diurnal cycle. Notably, more than half of the LSH events at midlatitudes are linked to extratropical cyclones. These findings demonstrate that large-drop heavy rainfall occurs not only over continental regions in summer, but also over midlatitude oceans in winter. These findings provide useful information for improving satellite precipitation retrieval algorithms and microphysical parameterizations in weather prediction models, particularly for better performance over midlatitude oceans.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104879"},"PeriodicalIF":8.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Alteration mineral information extraction based on image super-resolution technology","authors":"Chunyu Zhao ,&nbsp;Zhiqiang Xiao ,&nbsp;Yan Zhang ,&nbsp;Changjiang Yuan ,&nbsp;Jie Yang","doi":"10.1016/j.jag.2025.104872","DOIUrl":"10.1016/j.jag.2025.104872","url":null,"abstract":"<div><div>High-resolution remote sensing imagery is crucial for advancing earth science research. However, the scarcity of high-resolution data in specific non-visible spectral bands, such as short-wave infrared (SWIR) or thermal infrared (TIR), is challenge for various downstream tasks. To address this limitation, this study introduces a novel cross-band super-resolution (CBSR) method. This method improves the spatial resolution of targeted bands, specifically SWIR, within remote sensing images, and the methodology was tested with multi-band data from advanced spaceborne thermal emission and reflection radiometer (ASTER). The approach involves training a neural network on high-resolution visible and near-infrared single-band data, then the trained model is applied to generate high-resolution SWIR imagery. Validation was conducted over the Duolong Cu–Au porphyry district using ASTER imagery, focusing on mapping hydrothermal alteration. Through Bayesian optimization, the model achieved optimal performance with a peak signal-to-noise ratio of 43.17 dB, which is better than traditional methods. CBSR-reconstructed SWIR imagery, fused with principal component analysis, accurately delineated argillic alteration halos and ring structures. Furthermore, zero-shot transfer of the ASTER-trained model to Sentinel-2 imagery demonstrated the framework’s generalizability across sensor configurations. The proposed CBSR approach thus provides a robust, spectrally consistent mechanism for enhancing multi-resolution satellite data, with direct implications for mineral exploration, lithological mapping, and other domains reliant on high-fidelity SWIR information.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"144 ","pages":"Article 104872"},"PeriodicalIF":8.6,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}