International Journal of Applied Earth Observation and Geoinformation最新文献

{"title":"Enhancing the interpretability of port economic modeling via implicit spatial relationship discovery","authors":"Xiaoli Cai, Sheng Wu, Peixiao Wang, Hengcai Zhang, Shifen Cheng, Feng Lu","doi":"10.1016/j.jag.2026.105161","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105161","url":null,"abstract":"Modeling the driving mechanisms of economic activities among port cities helps reveal their interactions and spatial spillover effects, which is crucial for promoting coordinated regional economic development. Current mainstream models of these driving mechanisms are mostly based on machine learning integrated with the SHAP method, but often neglect spatial dependencies between samples—especially the implicit spatial relationships underlying port city economic activities. In recent years, AIS data has become an important tool for uncovering these implicit spatial relationships. Therefore, we propose the PortCity2Vec framework, based on AIS data and embedding representation learning, to explicitly capture implicit spatial relationships among port cities. Furthermore, we develop a spatial XGBoost model integrated with GeoShapley to incorporate these implicit spatial relationships, thereby revealing the driving mechanisms behind socioeconomic indicators and quantifying the core roles of spatial relationships and geographic features in the port economy. The results show that: (1) Implicit economic interactions among port cities extend beyond physical adjacency, indicating that port economy is influenced not only by physical proximity but also by connections within an implicit spatial structure; (2) Introducing socioeconomic indicators and geographic features of nearby port cities within the implicit spatial structure improves model accuracy, increasing R<ce:sup loc=\"post\">2</ce:sup> from 0.6554 to 0.8541; (3) The port economy correlates positively with cargo turnover and grain crop output, but negatively with forestry and meat output. These findings highlight the key roles of economic and transport intensity and reveal resource allocation gaps. (4) Embeddings of implicit spatial relationships and geographic features effectively capture regional potential economic connections and marginal contributions that traditional models struggle to identify, thereby enhancing both the performance and interpretability of the model.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"196 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146209369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards language-based retrieval of complex geospatial data: A case study on UK National geographic database","authors":"Hailun Xie, Arjun Biswas, Steve Coupland, Ben Dickens, Jeremy Morley, Hywel Williams","doi":"10.1016/j.jag.2026.105145","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105145","url":null,"abstract":"Retrieving granular information from large-scale geospatial databases is challenging and can require significant domain expertise, owing to complex data taxonomies and hierarchical data structures related to geometry and topology. In this research, a multi-agent system is developed that uses large language models (LLMs) for geospatial information retrieval based on natural language queries. The proposed solution employs LLMs within three agents that decompose data retrieval into sub-tasks: human instruction comprehension; data collection identification; and feature category screening. The three agents collaborate in a sequential workflow to accumulate knowledge and identify a pathway to the correct information within a hierarchical data structure. A data retrieval module subsequently interprets the search extent and retrieves data through API calls to the underlying databases. The proposed approach is evaluated in a case study with a large and complex geospatial database, the National Geographic Database operated by Ordnance Survey in the UK. Evaluation was based on a total of 83 sample queries, i.e. 40 human queries collected from volunteers, 40 synthetic queries generated by LLM, and 3 queries selected from a benchmark database. The proposed system answered majority of the queries successfully, namely 22 out of the 31 valid human queries, 29 out of 37 effective synthetic queries, and all 3 queries from the benchmark dataset. This demonstrates good potential for flexible data retrieval, locating a variety of geographical features from different data collections in response to natural language questions about tennis courts, public car parks, and restaurants, etc. The multi-agent solution was also evaluated using OpenStreetMap and the results demonstrate the transferability of the proposed method in handling different data taxonomies and structures. Our findings also highlight several research challenges around the “AI readiness” of documentation, complex geospatial data taxonomies, ambiguity in human language, and complex spatial reasoning. Overall, our study addresses two major research gaps: (1) the use of unstructured natural language to accurately retrieve geospatial information; and (2) the use of LLMs to navigate multiple heterogeneous datasets in a hierarchical data taxonomy.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"45 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Glacier mass balance heterogeneity in high Mountain Asia analyzed from synthetic aperture radar","authors":"Lei Huang, Ying Huang, Tobias Bolch, Lan Zhuang, Zhen Li, Drolma Lhakpa","doi":"10.1016/j.jag.2026.105155","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105155","url":null,"abstract":"Glaciers in High Mountain Asia (HMA) are important water sources for millions of people in arid regions. However, their mass balance exhibits strong regional heterogeneity. The reasons are still not well understood mainly due to limited high-resolution temperature and precipitation datasets in high-altitude zones. Here, we propose a glacier ablation and accumulation index based on firn and snow observation from Sentinel-1 synthetic aperture radar data, which represent the seasonal ablation and accumulation patterns across HMA. Evaluations of the index with the summer snow line, precipitation, and temperature records from supraglacial weather stations confirm their reliability. Comparisons to available mass balance data show that glaciers with the lowest ablation and lowest summer-accumulation index which are located in the center of the HMA region, have the most balanced state (+0.05 m w.e. a<ce:sup loc=\"post\">-1</ce:sup>). In contrast, glaciers with a high ablation and median summer-accumulation index, show highly negative mass balances (−0.47 m w.e. a<ce:sup loc=\"post\">-1</ce:sup>). Under similar ablation index, the type of glaciers with higher summer-accumulation index is more negative. This work provides novel methods and knowledge to understand and project the glacier mass balance heterogeneity in HMA.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"31 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deriving China’s beach slopes at a national scale: An automated and transferable Fourier-based framework using ICESat-2 data","authors":"Hao Xu, Nan Xu, Huichao Xin, Yue Ma, Ming Ni, Yongzhi Wang, Gaocong Li, Xiaojing Zhong, Peng Yu, Shuai Yuan, Yuan Li, Shanhang Chi, Chi Zhang, Qingquan Li","doi":"10.1016/j.jag.2026.105158","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105158","url":null,"abstract":"Beach slope is a fundamental morphometric parameter governing coastal dynamics, wave dissipation, and shoreline stability, and serves as a key basis for coastal hazard prediction, wave runup and overtopping assessment, and the design of coastal engineering structures. However, due to the limited spatial coverage and high costs of conventional monitoring techniques, no high-resolution, national-scale dataset of beach slopes has previously been available for China until now. In this study, we develop an automated and transferable framework for deriving beach slopes from ICESat-2 ATL03 photon data and produce the first systematic national-scale dataset of China’s sandy beach slopes. The workflow integrates (1) data preprocessing, including shoreline-orthogonal correction of ICESat-2 ground tracks, vertical datum harmonization to EGM2008, and selection of high-confidence photons (confidence ≥ 2); (2) adaptive photon clustering based on an OPTICS (Ordering Points To Identify the Clustering Structure) algorithm coupled with a moving-window filter for accurate beach photon extraction; and (3) slope inversion using low-order Fourier polynomial delineation of the foreshore combined with robust linear regression. The resulting dataset encompasses 688 along-track profiles covering 243 sandy beaches along China’s coastline. Validation against high-precision reference data, including RTK-GNSS surveys and DEM-derived slopes, yielded strong agreement (RMSE = 0.012, R2 = 0.89), demonstrating the reliability of the proposed method across diverse geomorphic settings. Spatially, the results reveal a distinct north–south attenuation pattern, with steeper, more variable slopes in temperate northern coasts and gentler, low-gradient beaches in the tropical south. This novel dataset provides the first quantitative characterization of beach-slope spatial patterns at the national scale, offering critical parameters for storm-surge modeling, coastal-erosion assessment, and sustainable coastal management. Furthermore, leveraging open-accessible, global-scale ICESat-2 data, this framework is designed for easy transferability across coastal regions, offering a scalable solution for worldwide beach monitoring and assessment.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"2 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An attention-aware map interaction framework based on eye tracking and generative models","authors":"Tianxin Wang, Ping Du, Pei Dang, Tao Liu, Pengpeng Li","doi":"10.1016/j.jag.2026.105151","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105151","url":null,"abstract":"Traditional map interaction methods (such as mouse clicks or touch operations) rely heavily on explicit input, which tends to interrupt users’ spatial cognitive processes and increase their cognitive load. Although eye-tracking technology can capture users’ attention distributions, existing methods generally struggle to infer deep semantic intentions from gaze behaviors and lack the ability to dynamically generate map content on the basis of real-time cognitive states. Therefore, this study proposes a perception-enhanced map interaction framework driven by user cognition and attention, in which gaze behavior is not treated as a direct control mechanism but is instead regarded as a cognitive cue. By quantifying interest values and performing cognitive reasoning with a large language model (LLM), and by dynamically generating map symbols using a LoRA-fine-tuned Stable Diffusion model, a closed-loop workflow from gaze analysis to map symbol rendering is established. A prototype system was developed and validated across three typical scenarios. The results show that the prediction accuracy of areas of interest achieved an average IoU of 0.7 and an F1 score of 0.8, while map interaction efficiency improved by approximately 26.34–36.38%. Compared with traditional mouse interaction methods, the task completion rate increased by approximately 19.7%, the cognitive load was significantly reduced, and the system usability score (SUS) was significantly greater. By understanding users’ attention distribution, this study enhances map visual representations and provides a feasible technical pathway for the transition of map interaction paradigms from passive response to active understanding.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"39 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Underestimated shrubland distribution in the Eurasian drylands","authors":"Li Liu, Yangjian Zhang, Zhoutao Zheng, Guang Zhao, Nan Cong, Huanhuan Liu","doi":"10.1016/j.jag.2026.105144","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105144","url":null,"abstract":"The arid and semi-arid regions of the Eurasian continent (the Eurasian arid region) are home to extensive shrublands and these shrublands are critical components of the regional biomes. However, identifying shrublands and distinguishing them from grasslands via remote sensing remains challenging due to their spectral and phenological similarity, as evidenced by the varying distribution areas and patterns of shrublands across each common land cover product. To address this, we combined a multi-strategy sampling framework with a phenology-pixel-based method to map shrubland distribution in the arid Eurasian region. We achieved a mean F1 score of 67.05%, notably higher than that of existing global land cover datasets. The total mapped shrubland area is approximately 427,643 km<ce:sup loc=\"post\">2</ce:sup>, exhibiting a clear latitudinal peak (30°–50°N) and multimodal longitudinal distribution pattern. In different biomes, climatic conditions—moisture or temperature—regulate the optimal phenological windows by driving functional trait divergence between shrubland and grassland. Background shrubland cover strongly determines identification accuracy. When shrubland coverage exceeds 60%, mapping accuracy shifts from “detectable” to “reliable”. Below this threshold, classification accuracy is limited by phenological noise and topography interference, whereas above it, canopy continuity enhances spectral separability and reduces terrain-related noise. This study demonstrates that shrub coverage, phenological timing, and terrain collectively regulate mapping accuracy. The phenology-optimized classification framework significantly outperforms existing common shrubland distribution datasets, especially in complex microtopography and transition zones. Improved shrubland mapping is critical for evaluating ecosystem health and investigating carbon cycling in arid regions.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"91 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to “Climate change weakened the productivity benefits from the forestry ecological engineering projects-induced greening in China” [Int. J. Appl. Earth Obs. Geoinf. 146 (2026) 105052]","authors":"Liang Zheng, Hao Wu, Anqi Lin, Jianzhong Lu, Xiaoling Chen","doi":"10.1016/j.jag.2026.105138","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105138","url":null,"abstract":"","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"35 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optical Flow-based temporal displacement correction for Time-Consistent Multi-Satellite wind field reconstruction","authors":"Sirui Lv, Xiaobin Yin, Yan Li, Qing Xu, Zhaohui Wang, Xingwei Jiang, Ning Wang","doi":"10.1016/j.jag.2026.105148","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105148","url":null,"abstract":"High-resolution ocean observations and numerical simulations are increasingly in demand. However, conventional multi-source remote sensing wind products often struggle to capture the spatiotemporal consistency and dynamic variability required for mesoscale and submesoscale oceanic studies. This paper proposes an Optical Flow-based Temporal Displacement Correction (OF-TDC) method to improve the temporal alignment and mitigate structural misalignment in global multi-satellite wind fields (MSWF). The method treats satellite wind fields as sequential images while utilizing ERA5 winds as a dynamic reference. To ensure consistent input quality for this process, a robust bias correction scheme combining hierarchical Bayesian shrinkage and dual-reference LOESS smoothing is introduced. OF-TDC then estimates advection trajectories of MSWF over time and projects satellite wind fields observed at different times to a unified reference time to complete temporal registration. Evaluations show robust performance under moderate winds of 4 to 20 m/s and effective correction over medium to long timescales, with error standard deviation (STD) reductions of 1° in direction and 0.03 m/s in speed. Tropical cyclone analysis shows error STD improvements of up to 0.19 m/s and 2.24°, respectively, indicating that stronger, compact cyclones enable more accurate OF tracking. Validations against independent GNSS-R data and heavy rainfall confirm significant robustness. OF-TDC enhances MSWF temporal consistency, especially in structured, moderate-evolution environments, facilitating integrated wind and air-sea interaction studies.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"59 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel MT-InSAR method for robust estimation of permafrost deformation by integrating u test and multitier network strategy: a case study of the Beiluhe region of the Qinghai–Tibet Plateau","authors":"Guanyou Gao, Qijie Wang, Ya Zhang, Kai Sun, Jiachen Li, Yutong Huo, Junjie Hao","doi":"10.1016/j.jag.2026.105143","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105143","url":null,"abstract":"Distributed scatterer interferometry (DSI) is an effective technique for improving InSAR-derived deformation quality in low-coherence permafrost regions. Reliable identification of statistically homogeneous pixels (SHPs) and deformation inversion through a two-tier network are key steps of DSI. However, existing SHP selection methods based on parametric hypothesis testing generally assume temporal stationarity of surface backscattering, which is often violated in permafrost regions due to freeze‒thaw processes in the active layer. In addition, the conventional two-tier network strategy tends to produce unstable inversion networks in decorrelated permafrost areas, thereby degrading deformation reliability. To address these limitations, this study proposes a robust coherent scatterer InSAR (RCSI) method. First, considering temporal variations in surface backscattering, a <ce:italic>U</ce:italic> test is developed to identify SHPs with similar temporal backscattering behavior. Second, a multitier network strategy is proposed, in which persistent scatterers (PS) and distributed scatterers (DS) candidates are evenly partitioned into multiple groups according to posterior coherence, and deformation is progressively estimated using robust M−estimators. The effectiveness of RCSI is quantitatively validated using both simulated data and Sentinel-1 observations over the Beiluhe region on the Qinghai–Tibet Plateau. The results show that the <ce:italic>U</ce:italic> test can effectively identify SHPs under non-stationary backscattering conditions. Compared with the two-tier network strategy, the multitier network strategy achieves a 19.9% improvement in deformation accuracy, as validated against in situ leveling measurements, and yields a 42.6% increase in the number of measurement points (MPs). Our study demonstrates that RCSI can significantly enhance the quality of InSAR-derived deformation in permafrost regions.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"211 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TextMCD: A mask-classification change detection network with multimodal vision–language supervision","authors":"Zhaoming Wu, Mingyong Cai, Xinsheng Zhang, Zhengchao Chen, Yixiang Li, Zeqing Wang, Yu Zhao, Xuewei Shi","doi":"10.1016/j.jag.2026.105152","DOIUrl":"https://doi.org/10.1016/j.jag.2026.105152","url":null,"abstract":"Change detection in remote sensing leverages temporally distinct imagery to identify alterations in the surface of regions of interest, and holds significant application value in areas such as environmental protection and land use. Existing change detection networks consider pixel-level and mask-level perspectives separately, and have achieved promising results. However, methods based on pixel-level change detection are susceptible to challenges, including the merging of change regions and the omission of small change masks. Mask classification based change detection methods, which rely on query predictions, are more susceptible to false changes. To mitigate these limitations, we propose TextMCD, a mask classification based change detection framework that integrates multimodal vision–language learning. Specifically, our network adaptively obtains potential change masks through queries and further constrains the semantic categories of predicted masks using the text label information of a single mask. Meanwhile, we propose a multimodal decoder based on ground truth mask attention mechanism. During the decoding phase, the ground truth is incorporated into the training process without affecting the validation. By combining the mask attention mechanism, the model simultaneously captures the location, category, and temporal embedding information of the masks, which enhances the semantic consistency of individual masks in the change detection process. To validate our method, we performed before-and-after category labeling of change masks on multiple binary change detection datasets. The quantitative analysis reveals a notable increase in F1 score across various datasets. Qualitative analysis further demonstrates the advantages of our network in addressing issues such as mask adhesion, small mask miss detection, and false changes. Our code is available at <ce:inter-ref xlink:href=\"https://github.com/WuChaseSea/TextMCD\" xlink:type=\"simple\">https://github.com/WuChaseSea/TextMCD</ce:inter-ref>.","PeriodicalId":50341,"journal":{"name":"International Journal of Applied Earth Observation and Geoinformation","volume":"24 1","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}