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

{"title":"TEBS: Temperature–Emissivity–Driven band selection for thermal infrared hyperspectral image classification with structured State-Space model and gated attention","authors":"Enyu Zhao ,&nbsp;Nianxin Qu ,&nbsp;Yulei Wang ,&nbsp;Caixia Gao ,&nbsp;Jian Zeng","doi":"10.1016/j.jag.2025.104710","DOIUrl":"10.1016/j.jag.2025.104710","url":null,"abstract":"<div><div>Thermal infrared hyperspectral images (TIR-HSIs) provide unique spectral insights that are often unattainable with visible imagery, making them invaluable for applications such as land cover classification and geological mapping. However, the high spectral redundancy in TIR-HSIs often leads to increased computational complexity and potential performance degradation. To address this issue, this paper proposed an unsupervised temperature–emissivity–driven band selection method (TEBS) for TIR-HSIs classification, which integrated a structured state-space model (SSM) and a gated attention mechanism (GAM). Specifically, a feature extraction (FE) module is firstly designed to separate land surface temperature (LST) and land surface emissivity (LSE) information, incorporating superpixel segmentation to extract multi-scale LST features. Subsequently, a weight computation (WC) module, leveraging SSM and GAM, is developed to generate robust band weights by sequentially leveraging multi-scale LST features. Finally, a band evaluation (BE) module is employed to assess the band selection results and optimize the model parameters. Experimental comparisons conducted on two datasets using four classic classifiers show that TEBS framework outperforms state-of-the-art (SOTA) methods in classification accuracy. These results underscore the potential of TEBS to advance land cover classification in thermal infrared hyperspectral imaging. The data and code will be made publicly available at: <span><span>https://github.com/Qu-NX/TEBS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104710"},"PeriodicalIF":7.6,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548544","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":"Multi-granularity representation learning with vision Mamba for infrared small target detection","authors":"Yongji Li ,&nbsp;Luping Wang ,&nbsp;Shichao Chen","doi":"10.1016/j.jag.2025.104645","DOIUrl":"10.1016/j.jag.2025.104645","url":null,"abstract":"<div><div>Heterogeneous environments and low Signal-to-Clutter Ratio (SCR) pose a challenge for Infrared Small Target Detection (IRSTD). Convolutional Neural Network (CNN) is constrained by the global view. Transformer with quadratic computational complexity struggles for local feature refinement. Inspired by the quad-directional scanning State Space Model (SSM) with linear complexity for long-range modeling, this research reconceptualizes the spatial and structural information of small targets in IR images. Multi-granularity features and long-range dependency of small targets are considered simultaneously. Specifically, we tailor a nested structure with cross-fertilization of global and local information. Each layer of the top-level pyramid network embeds a tiny well-configured contextual pyramid block to extract fine-grained features of small targets. The following Mamba module restructures the feature maps to derive coarse-grained features of “visual sentences”. The fusion of contextual information and local feature achieves precise localization of small targets. Furthermore, we propose the Asymmetric Convolution (AConv) for substituting the Depthwise Convolution (DWConv) in the Visual State Space (VSS) module and the regular convolution in each lateral connection of the nested pyramid network to alleviate the parameters and computation. Both qualitative and quantitative experiments demonstrate that our proposed model outperforms 12 recent baseline methods on two public datasets.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104645"},"PeriodicalIF":7.6,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557503","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":"Urban grey-green scales: A new perspective for assessing dynamic spatial trade-offs","authors":"Xi Wang ,&nbsp;Liang Zhou ,&nbsp;David López-Carr ,&nbsp;Yongze Song ,&nbsp;Hong Gao ,&nbsp;Tao Che ,&nbsp;Zhifeng Liu ,&nbsp;Wei Wei","doi":"10.1016/j.jag.2025.104708","DOIUrl":"10.1016/j.jag.2025.104708","url":null,"abstract":"<div><div>Urbanization has shaped a dynamic relationship between urban grey and green spaces, and this relationship will profoundly affect the stability and sustainability of the urban system. However, few studies have focused on the complex dynamics, spatial patterns, and dominant factors of the coordination between urban grey and green spaces. Therefore, this study develops a grey-green space trade-offs indicator (GGSCI) to assess the dynamic relationship between vegetated and non-vegetated areas during the growth of urban built-up areas. The GGSCI is implemented to evaluate the long-term dynamics of urban growth across 121 cities in the arid zone of northern China (ANC) from 1990 to 2020. We use Mean-Kendall trend analysis methods to capture the typical features of urban greening, and an interpretable machine learning model is combined to reveal the relative contributions of socioeconomic and natural environment indicators to the GGSCI. The results indicate that: the built-up area of ANC has expanded by 5.72 times from 1990 to 2020. Total grey space growth is 2.12 times that of green space. In addition, the relationship between grey and green spaces in ANC is moving from imbalance to balance, with the percentage of cities in imbalance dropping from a maximum of 23.28 % to 0 %. The trend of greening in urban centers is remarkable. We also reveal that socioeconomic and natural environment alternated as the dominant factors influencing changes in the GGSCI at different stages of urbanization, with AAP and NL contributing the most at 22.24 % and 20.21 %, respectively.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104708"},"PeriodicalIF":7.6,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534683","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 unified multimodal learning method for urban functional zone identification by fusing inner-street visual–textual information from street-view and satellite images","authors":"Jiajun Chen,&nbsp;Runyu Fan,&nbsp;Hongyang Niu,&nbsp;Zijian Xu,&nbsp;Jining Yan,&nbsp;Weijing Song,&nbsp;Ruyi Feng","doi":"10.1016/j.jag.2025.104685","DOIUrl":"10.1016/j.jag.2025.104685","url":null,"abstract":"<div><div>Urban functional zones (UFZ) are areas that divide urban space into specific uses based on the distribution of different human activities and infrastructure. UFZ mapping is to analyze the geographic information data of urban space, combine remote sensing images (RSI), point of interest (POI) data and other data sources, and use advanced spatial analysis technology to divide and visualize the UFZ. The intelligent interpretation of UFZ can provide support for urban management and planning. Previous studies on UFZ mainly focused on using remote sensing images and POI data, which can obtain the city’s macroscopic remote sensing visual features and the distribution of land use. However, these methods often ignore the inner-street details due to the absence of using inner-street perspective data and cannot capture the complex spatial relations between objects in complex urban scenes, resulting in unsatisfied UFZ results. For this purpose, we propose a unified multimodal learning method to interpret UFZ by combining remote sensing images, POI data, and street view data with inner-street details to provide a more comprehensive perspective to boost UFZ interpretation. To make full use of the inner-street perspective advantage of street view images (SVI), we not only use their visual features but also extract textual features that can reflect various human activities in street views through image captioning technology, better to capture the subtle socio-economic activity information in urban space. We conduct extensive experiments in Wuhan, Changsha, and Nanchang. The OA of this method on the test set reached 91.80%. Experimental results show a significant improvement in the model’s performance in interpreting UFZ.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104685"},"PeriodicalIF":7.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522757","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 multi-source remote sensing-based geocommunication tool for global flood monitoring and management","authors":"Ebrahim Hamidi ,&nbsp;Brad G. Peter ,&nbsp;Hamed Moftakhari ,&nbsp;Hamid Moradkhani","doi":"10.1016/j.jag.2025.104701","DOIUrl":"10.1016/j.jag.2025.104701","url":null,"abstract":"<div><div>Global warming is expected to increase the frequency of extreme flooding, making rapid and accurate flood mapping crucial for effective risk assessment. Many governmental agencies and organizations are developing flood risk assessment tools; however, due to the lack of observational records, some rely on probabilistic generated data, uncalibrated simulations, or terrain-based methods, all of which are subject to various types of uncertainty. Although remote sensing provides valuable flood data with global coverage, single-source reliance is constrained by satellite revisit rates, resolution, weather conditions, and sensor limitations. To address these challenges, this study introduces a user-friendly application on the Google Earth Engine (GEE) platform that enables near-real-time global flood mapping using a multi-source remote sensing approach. By leveraging optical and SAR imagery, the App ensures improved water detection accuracy and supports all-weather and day/night monitoring. Our results show SAR and optical flood inundation maps agree up to 80 %. Beyond flood mapping, the tool leverages GEE datasets to extract multi-disciplinary information, such as population exposure and affected residential, urban, and cropland areas, to support timely decision-making. For example, during the Sylhet, Bangladesh flood, the tool identified over 300,000 people potentially affected and approximately 600 km² of cropland inundated. This research presents one of the first global-scale, rapid, multi-source flood mapping tools tailored to both expert users and non-expert decision-makers. It offers a practical solution to current data limitations and supports more informed emergency response, planning, and climate resilience efforts to foster communication across scientific, policy, management, and operational communities.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104701"},"PeriodicalIF":7.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534684","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":"Quantifying the functional composition and potential resilience hotspots across a large latitudinal and environmental gradient in South American forests","authors":"Xiongjie Deng ,&nbsp;Danny E. Carvajal ,&nbsp;Rocío Urrutia-Jalabert ,&nbsp;Waira S. Machida ,&nbsp;Alice Rosen ,&nbsp;Huanyuan Zhang-Zheng ,&nbsp;David Galbraith ,&nbsp;Sandra Díaz ,&nbsp;Yadvinder Malhi ,&nbsp;Jesús Aguirre-Gutiérrez","doi":"10.1016/j.jag.2025.104704","DOIUrl":"10.1016/j.jag.2025.104704","url":null,"abstract":"<div><div>Accurately inferring plant functional trait composition, diversity, and redundancy across space and time is pivotal for understanding environmental change impacts on forests’ biodiversity and functioning. Here, we tested the capabilities of combining <em>in-situ</em> and remote sensing approaches to deliver accurate estimates of functional trait composition, diversity, and redundancy of temperate forest vegetation in South America (30°S to 53°S) considering leaf and stem morphological, nutrient, hydraulic, and photosynthetic traits. We identified hydrological stress, soil properties, and topography as key drivers of plant functional trait distribution and variation. Further, hydrological stress and soil properties were key determinants of functional diversity and redundancy across a large latitudinal gradient. Functional diversity peaked across Mediterranean forests, occupying between 30°S to 35°S. Functional diversity and redundancy were both high at latitudes between 35°S and 42°S, coinciding with Valdivian rainforests. Conversely, functional redundancy peaked between 42°S and 48°S, corresponding to Austral forests. Towards the southernmost extent of the study area, functional diversity and redundancy were both low between 48°S and 53°S, corresponding to the Magellanic subpolar forests. Our results highlight areas in South American temperate forests where both plant functional diversity and redundancy were maximal, hence potentially pointing towards areas more resilient to environmental change.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104704"},"PeriodicalIF":7.6,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522756","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":"Spatiotemporal patterns of the urban thermal environment and the impact of human activities in low-latitude plateau cities","authors":"Fei Zhao ,&nbsp;Maolin Zhang ,&nbsp;Shaoting Zhu ,&nbsp;Xingyi Zhang ,&nbsp;Sunjie Ma ,&nbsp;Yichen Gao ,&nbsp;Jisheng Xia ,&nbsp;Xinrui Wang ,&nbsp;Yiyang Zhang ,&nbsp;Sujin Zhang ,&nbsp;Xiaoqing Zhao ,&nbsp;Yang Shen","doi":"10.1016/j.jag.2025.104703","DOIUrl":"10.1016/j.jag.2025.104703","url":null,"abstract":"<div><div>Urbanization intensifies the surface urban heat island (SUHI) effect, impacting the urban thermal environment (UTE). This study focuses on Kunming, a low-latitude plateau city in China, to analyze the spatiotemporal evolution of its UTE using remote sensing data. The Cumulative Human Activity Intensity (CHAI) index, incorporating land use, nighttime lights, population density, GDP, and tourism activities, is introduced to assess human activity’s spatial impact on land surface temperature (LST). Key findings include: (1) The nighttime SUHI effect is more pronounced and spatially concentrated, with stronger LST warming and a northwestward shift of the SUHI core; (2) The impact of human activities on LST shows spatial heterogeneity, with urban areas experiencing stronger warming than suburban areas. Specifically, sparsely built areas (LCZ9) and open low-rise zones (LCZ6) contribute significantly to warming; (3) Human activities more strongly influence nighttime LST, with this effect intensified by the synergistic interaction between topographic and meteorological factors. This study offers a novel approach to quantifying diurnal and nocturnal human activity effects on LST, providing insights for optimizing UTE management.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104703"},"PeriodicalIF":7.6,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144514030","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":"Coupled InVEST-GTWR modeling reveals scale-dependent drivers of N and P export in a Chinese mountainous region","authors":"Zhiqiang Lin ,&nbsp;Shuangyun Peng ,&nbsp;Yuanyuan Yin ,&nbsp;Dongling Ma ,&nbsp;Rong Jin ,&nbsp;Jiaying Zhu ,&nbsp;Ziyi Zhu ,&nbsp;Shuangfu Shi ,&nbsp;Yilin Zhu","doi":"10.1016/j.jag.2025.104705","DOIUrl":"10.1016/j.jag.2025.104705","url":null,"abstract":"<div><div>Nitrogen (N) and phosphorus (P) export from non-point sources significantly threaten water quality in mountainous regions undergoing rapid agricultural intensification and urbanization. However, existing research often neglects multi-scale analyses across administrative levels and provides limited insight into the complex drivers of nutrient export in data-scarce mountainous regions. This study presents a novel integrated modeling framework by coupling the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model with Geographically and Temporally Weighted Regression (GTWR) to analyze N and P export dynamics in Yunnan Province from 2000 to 2019. We reveal a temporal turning point around 2011, with declining nutrient exports before 2011 followed by a rising trend linked to policy changes and intensified land use. Spatially, high N and P export clusters occur in densely populated, agriculturally intensive central and southeastern Yunnan, while forested northwestern areas exhibit low export. Prefecture-scale drivers are dominated by population density, fertilizer application, and industrial activity, whereas county-scale drivers highlight cropland area, precipitation, and terrain factors. Importantly, natural and anthropogenic factors interact to shape nutrient export patterns, underscoring the need for spatially differentiated management. The integration of InVEST-GTWR reflects methodological innovations that capture spatio-temporal non-stationarity and provide actionable insights for targeted nutrient pollution control in mountainous regions, with high model accuracy (R² = 0.98 at the prefecture scale and R² = 0.95 at the county scale).</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104705"},"PeriodicalIF":7.6,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517744","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":"High-resolution surface soil moisture retrieval: A hybrid machine learning framework integrating change detection and downscaling for precision water management","authors":"Zihao Wang ,&nbsp;Qi Gao ,&nbsp;Michele Crosetto ,&nbsp;Maria Jose Escorihuela","doi":"10.1016/j.jag.2025.104702","DOIUrl":"10.1016/j.jag.2025.104702","url":null,"abstract":"<div><div>Soil moisture (SM) is vital for comprehending the hydrological cycle and managing climatic extremes. Fine-scale accurate SM products hold more and more significant value to water management and precise agricultural irrigation. While in-situ measurements provide high accuracy, their limited spatial coverage and high costs necessitate alternative approaches. Remote sensing enables large-scale monitoring; however, satellite-based SM products have relatively lower spatial resolution, making them less suitable for practical applications. This study presents an innovative high-resolution surface soil moisture (SSM) retrieval framework combining machine learning (ML), change detection and downscaling (CD-DS) methods. The procedure is applied over Catalonia, Spain. The framework integrates Sentinel-1 SAR, Sentinel-2 normalized difference vegetation indices (NDVI), and DISPATCH background SSM data to generate 30-m resolution SSM. A novel backscatter difference variable, derived from the change detection method, improves model performance by addressing vegetation. The ML model was trained using in-situ SSM data collected from 2017 to 2021 and validated against independent in-situ measurement datasets. Among the evaluated algorithms, XGBoost model performed best, achieving an R² of 0.933 and RMSE of 0.023 cm³/cm³. Validation with ground measurements with different landcover types showed an average correlation of 0.63, a ubRMSE of 0.045 cm³/cm³, and minimal bias of 0.024 cm³/cm³. Notably, backscatter difference emerged as the second most important variable in the ML model after background SSM, highlighting its significance in improving SSM retrieval accuracy. Comparisons with data from 54 measurement sites, obtained during a 2015 field campaign, yielded an R value of 0.82, a RMSE of 0.06 cm³/cm³. Temporal analysis revealed strong consistency with in-situ data, capturing seasonal trends and abrupt changes after precipitation and irrigation events. Furthermore, the spatial distribution of SSM is closely aligned with irrigation type maps, showing higher SSM values in irrigated areas and lower values in rainfed regions. This approach delivers precise field-scale SSM estimates, making it a valuable tool for drought monitoring and modern agricultural practices.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104702"},"PeriodicalIF":7.6,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144514029","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":"Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea","authors":"Hyeongmok Lee ,&nbsp;Go-Eun Kim ,&nbsp;Woo-Jin Shin ,&nbsp;Yuyoung Lee ,&nbsp;Sanghee Park ,&nbsp;Kwang-Sik Lee ,&nbsp;Jina Jeong ,&nbsp;Seung-Ik Park ,&nbsp;Sungwook Choung","doi":"10.1016/j.jag.2025.104697","DOIUrl":"10.1016/j.jag.2025.104697","url":null,"abstract":"<div><div>The ⁸⁷Sr/⁸⁶Sr isotopic ratio has emerged as a valuable geochemical tracer in fields such as environmental forensics, archaeology, and provenance research. However, generating accurate and spatially continuous isoscape maps from sparse isotopic measurements remains a major challenge due to limited data availability and spatial heterogeneity. To address this, we propose a hybrid framework for ⁸⁷Sr/⁸⁶Sr isoscape mapping that integrates a kriging-based data augmentation method with a deep learning (DL) classifier. The kriging component generates synthetic training samples by interpolating sparse isotopic data while preserving underlying spatial correlations and geological anisotropy. These augmented data, along with spatial geological features (e.g., lithology, tectonic settings) and geochemical compositions, are used as input variables for training a feedforward deep neural network. The approach was applied to 409 soil samples collected across South Korea, and its performance was benchmarked against conventional kriging and convolutional neural networks (CNN). The proposed model achieved significantly higher classification accuracy (91.67%) compared to kriging-based and CNN-based models (76.7% and 86.7%, respectively). Furthermore, the isoscape outputs revealed meaningful isotopic patterns linked to geological and geomorphological controls, such as metamorphic rock distributions, fault density, and surface slope. This framework demonstrates the effectiveness of combining geostatistics with DL to improve predictive accuracy and interpretability in isotopic provenance research and environmental monitoring.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"142 ","pages":"Article 104697"},"PeriodicalIF":7.6,"publicationDate":"2025-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144510922","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}