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

{"title":"Spatial-and-local-aware deep learning approach for Ground-Level NO2 estimation in England with multisource data from satellite-based observations and chemical transport models","authors":"Siying Wang ,&nbsp;Shuangyin Zhang ,&nbsp;Dawei Wang ,&nbsp;Weifeng Li","doi":"10.1016/j.jag.2025.104506","DOIUrl":"10.1016/j.jag.2025.104506","url":null,"abstract":"<div><div>High-resolution near-surface NO₂ data are crucial for monitoring air pollution dynamics. Satellite-based machine learning models are commonly used to estimate NO₂ concentrations, but tailoring advanced deep learning techniques to specific environmental problems remains challenging. This study applies a two-stage deep learning approach to estimate ground-level NO₂ concentrations in England at a 1 km spatial resolution from 2019 to 2021. Initially, we imputed the TROPOMI NO₂ column density to a continuous 1 km resolution. We then developed an efficient spatial-and-local-aware deep learning network (SLNet) for NO₂ mapping by integrating the imputed TROPOMI NO₂ data with multi-source information from meteorology, chemical transport model (CTM) simulations, and other auxiliary predictors. To address the translation invariance of convolutional neural networks (CNNs), we combined a local channel to identify spatial heterogeneity in the model. Our imputed TROPOMI NO₂ surfaces, which initially covered only 34.12 % of valid data, achieved full coverage with reliability and continuity at 1 km spatial resolution. Cross-validation confirmed that the SLNet model outperformed other state-of-the-art methods in estimating ground-level NO₂. The prediction model achieved R² values of 0.914, 0.919, and 0.887 for 2019, 2020, and 2021, respectively, and performed well in urban regions. Additionally, the Shapley Additive Explanations (SHAP) method revealed that features such as satellite and CTM NO₂, precipitation, green space, and road density significantly contributed to estimations through both spatial and local channels. The mapping results closely aligned with ground-level observations and accurately captured spatial variations. This study advances NO₂ concentration estimation by applying adaptable deep learning techniques and enhances the understanding of air pollution dynamics.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104506"},"PeriodicalIF":7.6,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building the optimal hybrid spatial Data-Driven Model: Balancing accuracy and complexity","authors":"Emanuele Barca,&nbsp;Maria Clementina Caputo,&nbsp;Rita Masciale","doi":"10.1016/j.jag.2025.104478","DOIUrl":"10.1016/j.jag.2025.104478","url":null,"abstract":"<div><div>Mapping environmental variables is crucial for natural resource management. Researchers and scholars have continually advanced this field with modern techniques such as Integrated Nested Laplace Approximation (INLA), Deep Learning (DL), and Graph Neural Networks (GNN) models. While effective, these models often present a significant challenge due to their <em>black</em> nature, which obscures the process of generating final maps from raw data. Recent theoretical breakthroughs have shown that white/grey-box models can achieve the same level of accuracy as these advanced techniques, debunking the belief that complex models are necessarily the most accurate. Based on these findings, we have developed a methodology that employs a series of statistical tests and data analytics to identify essential features hidden in spatial data in order to assess the predictive model (of white/grey kind) that best approximates underlying spatial processes. This methodology profiles the model that better adapts to the data, aiding in the selection of the simplest model that achieves the desired accuracy, functioning similarly to a recommender system for model selection. Furthermore, the set of permissible models includes only regressive-like ones to clarify the data’s contribution to map construction and can be applied to a wide range of datasets. By reducing complexity, this approach enhances the transparency of the model’s results. Real-world dataset demonstrates this methodology’s remarkable ability to produce highly accurate results.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104478"},"PeriodicalIF":7.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fusing multiplatform topo-bathymetric point clouds based on a pseudo-grid model: A case study around Ganquan Island, South China sea","authors":"Fanlin Yang ,&nbsp;Xiaolin Yu ,&nbsp;Xiankun Wang ,&nbsp;Xiaozheng Mai ,&nbsp;Chunxiao Wang ,&nbsp;Anxiu Yang ,&nbsp;Dianpeng Su","doi":"10.1016/j.jag.2025.104492","DOIUrl":"10.1016/j.jag.2025.104492","url":null,"abstract":"<div><div>High-quality, full-coverage topographic bathymetric data is crucial for marine economic development and ecological environment protection. Due to the complex environment of land-sea transition zone, it is challenging to acquire comprehensive bathymetric topography using a single sensor. Multiplatform topographic bathymetric technology, such as airborne LiDAR bathymetry (ALB) and multibeam echo sounding (MBES), whose point clouds can be integrated to construct a complete model of land-sea transition zone. However, point cloud data from different sources may have certain differences in the digital description of the same target. Meanwhile, affected by factors such as registration error and sensor system error, there are data gaps in the registered point cloud, which hinders the subsequent reconstruction. To overcome these problems, a fusion method combining a pseudo-grid model is proposed to construct a high-quality, seamless topographic-bathymetric map. This paper’s contribution identifies non-overlapping ALB regions and generates anti-noise MBES simulated points (SPs) by constructing a pseudo-grid. Moreover, this paper focuses on establishing a point-to-SP model to eliminate the gaps and reduce the impact of registration errors on the fusion accuracy. To verify the effectiveness of the proposed method, four typical samples along with six reference samples exhibiting diverse features collected from Ganquan Island in the South China Sea are utilized in the experiment. The results show that the proposed algorithm can achieve ideal results in terms of the average root mean square error (RMSE) of the six reference samples, which is reduced from 0.41 m to 0.19 m. It is indicated that the true topography can be restored and the proposed method has advantages in accuracy and robustness.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104492"},"PeriodicalIF":7.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images","authors":"Peng Zhu,&nbsp;Hao Li,&nbsp;Pan Zheng","doi":"10.1016/j.jag.2025.104500","DOIUrl":"10.1016/j.jag.2025.104500","url":null,"abstract":"<div><div>Dust is one of the key factors influencing photovoltaic (PV) power generation. The ability to accurately capture PV dust information is essential for PV operation and sustainable utilization. This study employs uncrewed aerial vehicle (UAV) hyperspectral imaging to monitor PV dust deposition. To address the problems of information redundancy in hyperspectral data and the backpropagation neural network (BPNN) easily falling into local optimum, a high-precision UAV hyperspectral PV dust estimation method is proposed. The fractional order derivative (FOD) is applied to the spectral reflectance of PV dust accumulation, and a PV dust estimation model with sine map tuna swarm optimized backpropagation neural network (STSO-BPNN) is established, which is validated using UAV hyperspectral images and ground measured dust data. The results show that FOD improves the spectral signal-to-noise ratio, and the 0.2 order STSO-BPNN model achieves higher accuracy (R² = 0.95, RMSE = 0.79 g/m², RPIQ = 7.98). These findings provide a scientific basis for the rapid and accurate estimation and mapping of PV dust accumulation while proposing a novel strategy for efficient PV implementation and management.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104500"},"PeriodicalIF":7.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HI4HC and AAAAD: Exploring a hierarchical method and dataset using hybrid intelligence for remote sensing scene captioning","authors":"Jiaxin Ren ,&nbsp;Wanzeng Liu ,&nbsp;Jun Chen ,&nbsp;Shunxi Yin","doi":"10.1016/j.jag.2025.104491","DOIUrl":"10.1016/j.jag.2025.104491","url":null,"abstract":"<div><div>Remote sensing scene captioning is crucial for the deep understanding and intelligent analysis of Earth observation data. Many existing methods and datasets lack a fine-grained description of key geographical elements, fail to capture the full diversity of spatial relations, and are limited in their applicability to real-world geospatial scenarios. To address these shortcomings, we propose HI4HC (hybrid intelligence for remote sensing scene hierarchical captioning), a novel method that combines deep learning algorithms with expert knowledge to generate hierarchical captions for remote sensing scenes. This approach comprehensively describes scenes across three dimensions: geographical elements, spatial relations, and scene concepts, resulting in more accurate, detailed, and comprehensive captions. Leveraging HI4HC, we have constructed and made public a high-quality hierarchical caption dataset named AAAAD (adopt-amend-annihilate-add dataset). Extensive experiments show that AAAAD outperforms traditional single-level caption datasets in terms of the richness of geographical elements, the precision of spatial relations, and overall caption diversity, with improvements observed across 11 out of 13 evaluation metrics. Moreover, the hierarchical captions generated by HI4HC offer users the flexibility to organize information according to specific application needs such as imagery classification, change detection, multimodal understanding and cross-modal retrieval. This adaptability not only alleviates the semantic gap in imagery understanding but also plays an important role in advancing intelligent analysis of remote sensing imagery. AAAAD can be accessed through <span><span>https://github.com/jaycecd/HI4HC</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104491"},"PeriodicalIF":7.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated crevasse mapping for Alpine glaciers: A multitask deep neural network approach","authors":"Celia A. Baumhoer ,&nbsp;Sarah Leibrock ,&nbsp;Caroline Zapf ,&nbsp;Werner Beer ,&nbsp;Claudia Kuenzer","doi":"10.1016/j.jag.2025.104495","DOIUrl":"10.1016/j.jag.2025.104495","url":null,"abstract":"<div><div>Glacier crevasses are fractures in ice that form as a result of tension. Information on the location of crevasses is important for mountaineers and field researchers to plan a safe traverse over a glacier. Today, Alpine glaciers change faster than cartography can keep up with up-to-date manually created maps on crevasse zones. For the first time, this study presents an approach for automated crevasse mapping from high-resolution airborne remote sensing imagery based on a multitask deep neural network. The model was trained and evaluated over seven training and six test areas located in the Oetztal and Stubai Alps. By simultaneously preforming edge detection and segmentation tasks, the multitask model was able to robustly detect glacier crevasses of different shapes within different illumination conditions with a balanced accuracy of 86.2 %. Our approach is applicable to large-scale applications as demonstrated by creating high-resolution crevasse maps for the entire Oetztal and Stubai Alps for the years 2019/2020. Spatial and temporal transferability was proven by creating high-quality crevasse maps for all glaciers surrounding Großglockner, Piz Palü, and Ortler. The here presented datasets can be integrated into hiking maps and digital cartography tools to provide mountaineers and field researcher with up-to-date crevasse information but also inform modelers on the distribution of stress within a glacier.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104495"},"PeriodicalIF":7.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating multi-seasonal SAR and optical imagery for above-ground biomass estimation using the national forest inventory of Zambia","authors":"Kennedy Kanja ,&nbsp;Ce Zhang ,&nbsp;Peter M. Atkinson","doi":"10.1016/j.jag.2025.104494","DOIUrl":"10.1016/j.jag.2025.104494","url":null,"abstract":"<div><div>Mapping forest above-ground biomass (AGB) is crucial for monitoring forest ecosystems and assessing the success of conservation initiatives such as the REDD + carbon projects. Traditional field-based approaches to measuring AGB, however, face significant challenges, due to high financial costs and logistical constraints. Remote sensing, including both active and passive sensors, presents a promising and cost-effective alternative, yet its practical utility and accuracy for capturing forest AGB in diverse and complex ecosystems remains largely unexplored. This research used an extensive national forest inventory (NFI) dataset to evaluate the ability to map the AGB of the Miombo woodlands in Zambia across four agro-ecological zones using both multi-seasonal SAR (Sentinel-1A) and optical (Landsat-8 OLI) imagery. A multi-level experiment was designed to (i) compare the accuracy of AGB estimation using SAR and optical data when used independently, and in combination, using a Random Forest regression model, (ii) assess the effect of seasonality on the accuracy of AGB estimation when using SAR and optical datasets, and (iii) evaluate the effect of variation in climatic and environmental conditions on AGB estimation. Experimental results show that multi-seasonal images (across the rainy, hot and dry seasons) outperformed single-season and annual images. Combining SAR backscatter in the hot season, optical bands in the dry season, and vegetation indices in the hot season produced the most accurate AGB model (<em>R</em> = 0.69, MAE = 14.01 Mg ha⁻¹ and RMSE = 18.23 Mg ha⁻¹). The models performed distinctly across different agro-ecological zones (<em>R</em> = 0.44 – 0.79), suggesting that fitting local models could be beneficial. These results based on the extensive NFI of Zambia demonstrate that seasonal effects and fitting local models can lead to more accurate AGB estimation within the Miombo woodlands, which is of significance for ongoing REDD + carbon projects in Zambia and other African countries.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104494"},"PeriodicalIF":7.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An integrated object-based sampling approach for validating non-contiguous forest cover maps in fragmented tropical landscapes","authors":"Chima Iheaturu ,&nbsp;Vladimir Wingate ,&nbsp;Felicia Akinyemi ,&nbsp;Chinwe Ifejika Speranza","doi":"10.1016/j.jag.2025.104497","DOIUrl":"10.1016/j.jag.2025.104497","url":null,"abstract":"<div><div>Validating forest cover maps is essential for evidence-based conservation and sustaining ecosystem services. However, complex spatial patterns in fragmented tropical forest landscapes—often comprising non-contiguous forest patches, interspersed with agricultural lands and other land cover types—pose considerable difficulties for accuracy assessment using conventional techniques. To address this, we developed an integrated object-based sampling (IOBS) method that combines stratified random sampling, proportional allocation, and sample distance optimization. The IOBS method was applied to assess the accuracy of the Japan Aerospace Exploration Agency (JAXA) global 25 m PALSAR-2/PALSAR forest/non-forest (FNF) 2020 map across 14 ecoregions in Nigeria. Its performance was compared to simple random, systematic, and stratified random sampling using the coefficient of variation (CV), heterogeneity index (HI), and true accuracy metrics. IOBS demonstrated substantially higher spatial variability (CV = 109.37) and heterogeneity (HI = 0.21) compared to other methods (CV = 28.84–53.93, HI = 0.05–0.11). The IOBS estimated an accuracy of 81.1 %, closely aligning with the true accuracy of 82.4 % and outperforming other methods (75.3 %–79.7 %). The higher performance of IOBS stems from its ability to capture a broad range of forest conditions—from extensive contiguous cover to small, fragmented patches—while minimizing spatial autocorrelation through distance optimization. By better representing local heterogeneity, IOBS offers a robust and precise framework for validating categorical forest cover maps in complex tropical landscapes, advancing accuracy assessment practices for remote sensing applications.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104497"},"PeriodicalIF":7.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced NDVI prediction accuracy in complex geographic regions by integrating machine learning and climate data—a case study of Southwest basin","authors":"Zehui Zhou ,&nbsp;Jiaxin Jin ,&nbsp;Bin Yong ,&nbsp;Weidong Huang ,&nbsp;Lei Yu ,&nbsp;Peiqi Yang ,&nbsp;Dianchen Sun","doi":"10.1016/j.jag.2025.104498","DOIUrl":"10.1016/j.jag.2025.104498","url":null,"abstract":"<div><div>The normalized difference vegetation index (NDVI) is a vital metric for assessing vegetation growth, yet accurate prediction remains challenging, particularly in regions with complex geographic and climatic conditions. Machine learning methods offer promise but are often hindered by sensitivity to model structure, input parameters, and training samples. To address these limitations, this study developed an NDVI time-series prediction optimization model, LSKRX, which integrates multiple machine learning algorithms with local geographic and climatic data. Using the Southwest Basin of China as a case study, dominant climatic factors were identified through sub-basin analysis, and machine learning models were constructed to link NDVI with these factors. The LSKRX model demonstrated significant improvements in prediction accuracy compared to single-model approaches, with the most notable enhancement in BIAS. Spatially, the model’s predictions aligned closely with observed values, particularly in the middle and lower reaches of the Yarlung Zangbo River. The model performed exceptionally well in winter (CC: 0.964) and summer (CC: 0.918) and achieved optimal accuracy in alpine regions at altitudes of 4000–5000 m (CC: 0.900). By leveraging the strengths of multiple machine learning models, the LSKRX model enhances NDVI prediction reliability under complex mountainous and alpine conditions, providing a robust tool for precise ecological assessment and management.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104498"},"PeriodicalIF":7.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scientists yet to consider spatial correlation in assessing uncertainty of spatial averages and totals","authors":"Alexandre M.J.-C. Wadoux ,&nbsp;Gerard B.M. Heuvelink","doi":"10.1016/j.jag.2025.104472","DOIUrl":"10.1016/j.jag.2025.104472","url":null,"abstract":"<div><div>High-resolution maps of climate and ecosystem variables are essential for supporting terrestrial carbon stocks and fluxes estimation, climate change mitigation, and ecosystem degradation assessment. These maps are usually created using remotely sensed data obtained from various types of imagery and sensors. The remote sensing data typically serve as covariates to deliver spatially explicit information using machine learning algorithms. Often the uncertainty associated with the maps is also quantified, for instance by prediction error variance maps or by maps of the lower and upper limits of a prediction interval. In addition, these products are often aggregated to regional, national, or global scales relevant to climate policy, natural resource inventory, and measurement, reporting, and verification (MRV) frameworks. Quantifying uncertainty in aggregated products is crucial as it is necessary to assess their value and evaluate whether changes and trends in aggregated estimates are statistically significant. However, we argue that such uncertainty is frequently inaccurately assessed due to the neglect of spatial correlation in map errors. This critical methodological issue has been overlooked in most large-scale mapping studies.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"139 ","pages":"Article 104472"},"PeriodicalIF":7.6,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}