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

{"title":"Temperature and water limitation exhibit divergent controls on grassland greening across global aridity gradients","authors":"Gongxin Wang ,&nbsp;Changqing Jing ,&nbsp;Xiuliang Yuan ,&nbsp;Tim Van de Voorde ,&nbsp;Yuqing Shao ,&nbsp;Tong Dong ,&nbsp;Ping Dong","doi":"10.1016/j.jag.2025.104806","DOIUrl":"10.1016/j.jag.2025.104806","url":null,"abstract":"<div><div>Grasslands play a crucial role in carbon cycling, biodiversity conservation, and human welfare. Identifying the drivers of grassland greening is essential for forecasting ecosystem responses to future climate change and developing effective adaptation strategies. Grasslands worldwide have experienced pronounced greening trends over recent decades. Despite this widespread phenomenon, the underlying biophysical mechanisms and dominant drivers remain insufficiently understood. By integrating satellite observations with model simulations, we show consistent increases in global grassland leaf area index (LAI) across both historical periods and future scenarios. A sustained increase in summer LAI is identified as the primary driver of grassland greening, contributing approximately 43.28% to the overall trend. Grassland greening exhibits strong spatial heterogeneity, with humid regions accounting for the largest contribution (i.e., 67.27%). Correlation analysis, structural equation modeling, and ridge regression reveal distinct regional differences in the dominant drivers across aridity gradients. Soil moisture (SM) emerges as the primary driver in arid regions, while temperature plays a more prominent role in semi-arid areas. In sub-humid and humid regions, vapor pressure deficit (VPD) exerts a stronger influence on grassland LAI dynamics. Moreover, the synergistic effect of temperature and VPD enhances summer greening, particularly in humid regions and high-latitude areas of the Northern Hemisphere. Notably, the influence of VPD transitions from inhibitory in arid regions to facilitative in humid environments. In contrast, the role of SM in shaping vegetation dynamics weakens progressively along the aridity gradient. These findings advance our understanding of how grassland ecosystems respond to varying hydroclimatic conditions and offer key insights for forecasting vegetation dynamics under future climate change.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104806"},"PeriodicalIF":8.6,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889933","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":"Decoding lake water eutrophication using an innovative dynamic model pool framework in Erhai Lake","authors":"Wei Si ,&nbsp;Zhixiong Chen ,&nbsp;Chi Yung Jim ,&nbsp;Ngai Weng Chan ,&nbsp;Mou Leong Tan ,&nbsp;Bingbing Liu ,&nbsp;Dong Liu ,&nbsp;Lifei Wei ,&nbsp;Shaoyong Wang ,&nbsp;Fei Zhang","doi":"10.1016/j.jag.2025.104808","DOIUrl":"10.1016/j.jag.2025.104808","url":null,"abstract":"<div><div>Rapid global urbanization has led to water eutrophication, threatening the stability of aquatic ecosystems stability. Chlorophyll-a (Chla), a key indicator of algal biomass, is a widely recognized as a metric for eutrophication. However, existing remote sensing retrieval methods face limitations in addressing complex environmental variations. This study developed an innovative Dynamic Model Pool (DMP) framework to optimize water quality prediction performance dynamically. Using Sentinel-2 satellite imagery and monthly in-situ Chla measurement data from Erhai located in Southwest China spanning 2018 to 2020, this study tested the effectiveness of the DMP framework. The results demonstrated that: (1) The DMP framework dynamically selected the optimal model based on data-specific characteristics. In 2018, the CBR model achieved the highest accuracy, while in 2019, GBR and XGBR were the most accurate. In 2020, GBR outperformed other models. (2) Spatiotemporal Chla distribution maps recorded consistently higher concentrations in the south part of lake, while the central part showed minimal level and variation. (3) Seasonal precipitation and temperature variations and policy implementation were key drivers of Chla concentration changes. Seasonal variations in precipitation and temperature collectively influenced the nutrient input and dilution dynamics in Erhai. Meanwhile, policy interventions implemented between 2018 and 2022, such as pollution interception and wastewater treatment, substantially decreased nutrient inflows during flood seasons and effectively limited nutrient accumulation.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104808"},"PeriodicalIF":8.6,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887474","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":"Deep learning-based surface deformation tracking with interferometric fringes: A case study in Taiwan","authors":"Shih-Teng Chang ,&nbsp;Shih-Yuan Lin ,&nbsp;Yu-Ching Lin","doi":"10.1016/j.jag.2025.104796","DOIUrl":"10.1016/j.jag.2025.104796","url":null,"abstract":"<div><div>Monitoring surface deformation is critical for understanding and mitigating natural and anthropogenic hazards, such as landslides and subsidence. Although Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR) provides detailed displacement measurements, its application in continuous monitoring remains constrained by high computational demands and complex data processing, often interrupting observation continuity. To address these challenges, this study proposes a deep learning-based method that processes wrapped Differential InSAR (D-InSAR) interferograms to directly detect surface deformation patterns<em>.</em> A Fringe-Labeling Model (FLM) was developed to identify deformation regions, followed by a Fringe-Detection Model (FDM) using Faster Region-based Convolutional Neural Networks (Faster R-CNN) to classify deformation magnitudes. The method achieved an average mean Average Precision (mAP) of 83.9% in Central Taiwan. Temporal transferability was validated by detecting deformation one year beyond the original MT-InSAR observation period. Spatial transferability was confirmed by applying the model to Northern Taiwan, where an F1 score of 78.74% was achieved while effectively identifying both uplift and subsidence. By enabling deformation detection across different magnitudes, time periods, and regions, the proposed framework offers a scalable and transferable solution for extending MT-InSAR-based surface hazard tracking.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104796"},"PeriodicalIF":8.6,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887473","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":"DisasterAdaptiveNet: A robust network for multi-hazard building damage detection from very-high-resolution satellite imagery","authors":"Sebastian Hafner ,&nbsp;Sebastian Gerard ,&nbsp;Josephine Sullivan ,&nbsp;Yifang Ban","doi":"10.1016/j.jag.2025.104756","DOIUrl":"10.1016/j.jag.2025.104756","url":null,"abstract":"<div><div>Earth observation satellites play a crucial role in disaster response and management, offering timely and large-scale data for damage assessment. Recent studies have demonstrated the potential of deep learning techniques for automated building damage detection from satellite imagery, often based on the xBD dataset. This high-quality dataset features bi-temporal very-high-resolution image pairs of several disaster events. Notably, several studies have proposed new network architectures and demonstrated their improved performance on xBD. Although such highly engineered model-centric approaches achieve promising results on the original dataset split of xBD, we show that they underperform on a new event-based split, which evaluates them on unseen events. To reduce this generalization gap, we propose to follow a data-centric approach. For this, we first derive a simplified baseline method from the winning solution of the xView2 competition, with greatly reduced complexity. With a simple adjustment to this baseline method, we incorporate readily available disaster-type information, allowing it to account for disaster-specific damage characteristics. We evaluate the resulting disaster-adaptive model on the event-based split of xBD and demonstrate its improved ability to generalize to unseen events compared to several competing methods. These results highlight the potential of our data-centric approach for practical and robust building damage assessment in real-world disaster scenarios. Code including the strong baseline model is available at: <span><span>https://github.com/SebastianHafner/DisasterAdaptiveNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104756"},"PeriodicalIF":8.6,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878291","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":"Progressive Self-Optimization Network: An unsupervised change detection method for VHR optical remote sensing imagery","authors":"Yuzhen Shen ,&nbsp;Francesca Bovolo ,&nbsp;Yuchun Wei ,&nbsp;Xudong Rui","doi":"10.1016/j.jag.2025.104792","DOIUrl":"10.1016/j.jag.2025.104792","url":null,"abstract":"<div><div>Change detection in very-high-resolution (VHR) remote sensing imagery has consistently been a focus and challenge within the remote sensing community. We present a novel unsupervised method named Progressive Self-Optimization Network. In this method, a new sample strategy is developed based on the initial change detection across three feature domains: spectral, deep, and class signal, to capture the “weak-to-strong” change signals and collect training samples with high accuracy. A new lightweight convolutional neural network is designed by partially replacing traditional convolutional layers with weight-shared partial convolution. To detect changes, a progressive self-optimization pattern is proposed based on the “weak-to-strong” change signals. This pattern detects changes gradually from regions with weak and strong change signals to regions with moderate change signals in a progressive manner. During this progressive process, detection results from each progression are integrated with “weak-to-strong” change signals to reselect training samples for the transfer training in the following progression, thus attempting to optimize the lightweight network. The final change map is generated by fusing all progression results. Five open VHR datasets and fourteen state-of-the-art unsupervised methods validate the proposed method.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104792"},"PeriodicalIF":8.6,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864209","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":"Spaceborne remote sensing effectively maps species richness across taxonomic groups in a mountain landscape","authors":"Cornelius Senf ,&nbsp;Lisa Geres ,&nbsp;Tobias Richter ,&nbsp;Kristin Braziunas ,&nbsp;Felix Glasmann ,&nbsp;Rupert Seidl ,&nbsp;Sebastian Seibold","doi":"10.1016/j.jag.2025.104797","DOIUrl":"10.1016/j.jag.2025.104797","url":null,"abstract":"<div><div>Biodiversity decline due to global change poses a pressing challenge for conservation efforts worldwide. To improve the efficiency of conservation projects, spatially explicit information on species richness is needed, yet this information is challenging to generate from traditional biodiversity assessments. To fill this gap, we here explored the potential of spaceborne remote sensing techniques, including Sentinel-1, Sentinel-2 and EnMAP, for mapping species richness across four distinct taxonomic groups (fungi, plants, insects and birds) in a complex mountain landscape in the German Alps. We used all sensors individually, as well as different combinations of data (Sentinel-1/2, EnMAP/Sentinel-1/2), and compared predictions to predictions based on LiDAR data – a well-proven standard in mapping species richness. Our results showed that a combination of EnMAP/Sentinel-1/2 performed as well or even better than airborne LiDAR data for predicting species richness, but predictive accuracies of individual spaceborne models were substantially lower. This suggests that optical, radar and hyperspectral data carry complementary information and combining this information unleashes the full potential of spaceborne data for species richness mapping. However, validating models by habitat type revealed higher errors within habitat types (i.e., forest or open habitat), especially for immobile species (fungi and plants) that likely vary at smaller spatial scales than the resolution of the spaceborne systems used in this study. Overall, our findings highlight the potential of spaceborne remote sensing for large-scale biodiversity assessments, offering valuable insights into spatial biodiversity patterns and their changes over time.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104797"},"PeriodicalIF":8.6,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878292","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":"Instructor–Worker large language model system for policy recommendation: A case study on air quality analysis of the January 2025 Los Angeles wildfires","authors":"Kyle Gao ,&nbsp;Dening Lu ,&nbsp;Liangzhi Li ,&nbsp;Nan Chen ,&nbsp;Hongjie He ,&nbsp;Jing Du ,&nbsp;Linlin Xu ,&nbsp;Jonathan Li","doi":"10.1016/j.jag.2025.104774","DOIUrl":"10.1016/j.jag.2025.104774","url":null,"abstract":"<div><div>The Los Angeles wildfires of January 2025 caused more than 250 billion dollars in damage and lasted for nearly an entire month before containment. Following our previous work, the Digital Twin Building, we modify and leverage the multi-agent Large Language Model (LLM) framework as well as the cloud-mapping integration to study the air quality during the Los Angeles wildfires. Recent advances in large language models have allowed for out-of-the-box automated large-scale data analysis. We use a multi-agent large language system comprised of an Instructor agent and Worker agents. Upon receiving the users’ instructions, the Instructor agent retrieves the data from the cloud platform and produces instruction prompts to the Worker agents. The Worker agents then analyze the data and provide summaries. The summaries are finally input back into the Instructor agent, which then provides the final data analysis. We test this system’s capability for data-based policy recommendation by assessing our Large Language Model System with Instructor–Worker Architecture’s health recommendations and numerical summarizations based on the air quality data during the Los Angeles wildfires.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104774"},"PeriodicalIF":8.6,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864206","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":"HyperEst: Context-aware self-supervised pretraining for hyperspectral and multispectral water quality estimation","authors":"Chenxi Luo ,&nbsp;Wei Xiang ,&nbsp;Kang Han ,&nbsp;Lu Yu ,&nbsp;Yiqing Guo ,&nbsp;S.L. Kesav Unnithan ,&nbsp;Xiubin Qi ,&nbsp;Nagur Cherukuru","doi":"10.1016/j.jag.2025.104761","DOIUrl":"10.1016/j.jag.2025.104761","url":null,"abstract":"<div><div>Accurate retrieval of water quality parameters (WQPs) from remote sensing imagery is essential for large-scale aquatic monitoring. However, existing models often suffer from limited generalizability across diverse optical water types, reliance on scarce labeled data, and sensitivity to input variability from different sensors. This paper proposes HyperEst, a self-supervised learning (SSL) framework designed to overcome these challenges. The core of our framework is a novel universal context-aware autoencoder (UCAA), which is pretrained on vast unlabeled hyperspectral imagery using a unique single-pixel reconstruction strategy and a multi-scale diffusion loss to promote robust spectral-spatial feature learning. The pretrained UCAA acts as a strong prior, enhancing generalization to unseen areas and reducing outlier errors. Furthermore, we introduce the weighted mean improvement (WMI), a metric designed for a balanced performance assessment across multiple WQPs, including Chlorophyll-a, total suspended solids, and colored dissolved organic matter. Once fine-tuned, HyperEst achieves state-of-the-art performance. Our model improves <span><math><mrow><mi>l</mi><mi>o</mi><mi>g</mi><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></mrow></math></span> by 1.87%–3.75% and reduces prediction bias by 26.24%–65.47% in terms of WMI. The experimental results highlight the scalability and robustness of HyperEst, representing a step forward in developing globally applicable models for water quality estimation from spaceborne observations.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104761"},"PeriodicalIF":8.6,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864207","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":"Data fusion-based improvements in empirical regression and machine learning for global daily ∼ 8 km resolution sea surface nitrate estimation and interpretation","authors":"Aifen Zhong ,&nbsp;Difeng Wang ,&nbsp;Fang Gong ,&nbsp;Jingjing Huang ,&nbsp;Zhuoqi Zheng ,&nbsp;Xianqiang He ,&nbsp;Qing Zhang ,&nbsp;Qiankun Zhu","doi":"10.1016/j.jag.2025.104800","DOIUrl":"10.1016/j.jag.2025.104800","url":null,"abstract":"<div><div>Assessing sea surface nitrate (SSN) concentrations and dynamics is crucial for understanding marine ecosystem health, yet optical remote sensing of SSN remains challenging because of the lack of distinct spectral features. While various global-scale SSN regression and machine learning algorithms based on SSN-environment variable relationships have been developed, the prediction accuracy and spatiotemporal resolution of their applications continue to face limitations. Additionally, there has been relatively little reporting on the interannual variability of global SSN in previous studies. Here we aim to enhance the accuracy and spatial resolution of SSN retrievals by developing improved regression and machine learning models, enabling the generation of global daily ∼ 8 km SSN products from satellite and model data. To construct the empirical regression models, the global ocean was divided into five regions on the basis of the relationship between sea surface temperature (SST) and SSN: 80° S to 40° N, the North Pacific, the North Atlantic, the Arabian Sea, and the eastern equatorial Pacific. After adding SSN-related physical variables, high-accuracy regional empirical models are developed, with root mean square deviations (RMSDs) of 1.641, 2.701, 1.221, 1.298, and 2.379 μmol/kg for the studied regions. For the machine learning models, seven algorithms, namely, extremely randomized trees (ET), multilayer perceptron (MLP), stacking random forest (SRF), Gaussian process regression (GPR), support vector machine (SVM), gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost) algorithms, were tested. After modeling, validation, and extensive tests using independent cruise dataset, the XGBoost model outperformed others (RMSD = 1.189 μmol/kg) and bypassed the need for regional segmentation. Mechanistic analysis revealed the driving variables influencing SSN in both regional empirical and XGBoost models, improving interpretability. Comparative validation confirmed that our models surpass traditional approaches in accuracy and applicability, demonstrating their potential to advance global SSN monitoring. Using XGBoost-derived products, we find a slight weak decreasing trend in SSN over 23 years. The proposed robust and explainable SSN retrieval models have the potential to assist in ocean environmental management.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104800"},"PeriodicalIF":8.6,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864208","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 pregeneration–recognition method of detecting weak seafloor echoes for full-waveform airborne LiDAR bathymetry","authors":"Yadong Guo ,&nbsp;Wenxue Xu ,&nbsp;Yanxiong Liu ,&nbsp;Fanlin Yang ,&nbsp;Xue Ji ,&nbsp;Yikai Feng ,&nbsp;Qiuhua Tang","doi":"10.1016/j.jag.2025.104798","DOIUrl":"10.1016/j.jag.2025.104798","url":null,"abstract":"<div><div>Full-waveform airborne LiDAR bathymetry (ALB) technology, in which the analyzed waveforms reflect the temporal positions and attribute information of targets, is effective in shallow water. However, weak seafloor echoes in full-waveform data induced by environmental and device characteristics are confused with noise signals, leading to difficulties in seafloor detection. This paper proposes a pregeneration–recognition method of detecting weak seafloor echoes for ALB. First, a two-stage local maximum algorithm is developed to identify potential seafloor echoes in waveforms and to pregenerate points. Then, an adaptive ellipsoidal neighborhood related to the point density is used to select neighborhood points, and eigenvalue-based spatial features are calculated. Finally, a back propagation neural network (BPNN) model is constructed using the points generated from surface–seafloor shots, and the seafloor points in seafloor-undefined shots are obtained by optimizing the BPNN results. The proposed method is verified on four swaths collected via the Optech Aquarius ALB system near Wuzhizhou Island and Ganquan Island in the South China Sea. The numbers of additional points detected with the proposed method near these two islands increase by 195.9 % and 40.1 % compared with the Aquarius system, which is better than the Richardson–Lucy deconvolution method. The coverages and maximum depth of seafloor points are improved and the accuracy evaluations demonstrate the credibility of the results. Therefore, the proposed pregeneration–recognition method can effectively improve the detection rate for weak seafloor echoes and the depth performance of ALB systems. Future research will focus on mitigating the impact of seafloor topography on the proposed method to expand its application scenarios.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"143 ","pages":"Article 104798"},"PeriodicalIF":8.6,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144860327","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}