IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing最新文献

{"title":"A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping","authors":"Yi He;Hesheng Chen;Qing Zhu;Qing Zhang;Lifeng Zhang;Tao Liu;Wende Li;Huaiyuan Chen","doi":"10.1109/JSTARS.2025.3525633","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3525633","url":null,"abstract":"The existing landslide recognition methods mainly focus on the use of spectral bands of optical remote sensing and machine learning base classifiers, which are insufficient in landslide characterization in complex scenes, resulting in a high missed and false detection of landslides. In this article, we develop a landslide recognition framework, which combines the multidimensional feature advantages of spectral, terrain, and texture of optical satellite images, and constructs a heterogeneous ensemble learning method for landslide mapping. First, we construct a landslide multidimensional feature dataset using Sentinel-2A and Advanced Land Observing Satellite digital elevation model data. Then, we construct a heterogeneous ensemble learning landslide recognition method, which combines the advantages of fully convolutional network, U-Net, and attention U-Net base classifiers to fully learn the multidimensional features of landslides. Finally, we evaluate the performance of the landslide recognition framework in the Bailongjiang River Basin complex scenes. The experimental results show that integrating the multidimensional features of spectral, terrain, and texture and using the heterogeneous ensemble learning method can reduce the missed and false detection of landslides in complex scenes. Specifically, compared with using only spectral bands, integrating spectral bands, spectral indexes, terrain factors, and texture indexes achieves the highest Recall, Kappa, F1-score, and MIoU in testing areas, and missed alarm (MA) is reduced by 15.56%. Compared with deep learning base classifiers, the constructed heterogeneous ensemble learning demonstrates improvements in Recall ranging from 41.67% to 69.89%, and MA is reduced from 52.17% to 30.11%. This study provides a new idea for high-precision landslide recognition in complex environments.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3746-3765"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10824934","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing the Spatial Resolution of Sentinel-2 Images Through Super-Resolution Using Transformer-Based Deep-Learning Models","authors":"Alireza Sharifi;Mohammad Mahdi Safari","doi":"10.1109/JSTARS.2025.3526260","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3526260","url":null,"abstract":"Satellite imagery plays a pivotal role in environmental monitoring, urban planning, and national security. However, spatial resolution limitations of current satellite sensors restrict the clarity and usability of captured images. This study introduces a novel transformer-based deep-learning model to enhance the spatial resolution of Sentinel-2 images. The proposed architecture leverages multihead attention and integrated spatial and channel attention mechanisms to effectively extract and reconstruct fine details from low-resolution inputs. The model's performance was evaluated on the Sentinel-2 dataset, along with benchmark datasets (AID and UC-Merced), and compared against state-of-the-art methods, including ResNet, Swin Transformer, and ViT. Experimental results demonstrate superior performance, achieving a peak signal-to-noise ratio (PSNR) of 33.52 dB, structural similarity index (SSIM) of 0.862, and signal-to-reconstruction error ratio (SRE) of 36.7 dB on Sentinel-2 RGB bands. The proposed method outperforms state-of-the-art approaches, including ResNet, Swin Transformer, and ViT, on benchmark datasets (Sentinel-2, AID, and UC-Merced). The results demonstrate that the proposed method achieves superior performance in terms of PSNR, SSIM, and SRE metrics, highlighting its effectiveness in revealing finer spatial details and improving image quality for practical remote sensing applications.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"4805-4820"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10829708","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection","authors":"Shengning Zhou;Genji Yuan;Zhen Hua;Jinjiang Li","doi":"10.1109/JSTARS.2025.3526208","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3526208","url":null,"abstract":"Benefiting from continuous innovations in deep learning algorithms, the accuracy of building change detection (BCD) in remote sensing (RS) has significantly improved. Numerous networks combining CNN and transformer architectures have emerged, yet effectively balancing local detail and global context features remains a topic of ongoing discussion. Furthermore, accurately leveraging edge information within RS images to enhance the recognition of structural changes in buildings is another critical challenge. To address these issues, this article proposes a BCD network based on dynamic gate fusion and edge graph perception (DGFEG). First, a hybrid backbone, MCTrans, is employed as the encoder to extract multiscale detailed features and global positional information of buildings. Second, a dynamic gate fusion module is introduced to dynamically weight and fuse the concatenated and differential features obtained by the encoder, enhancing the semantic representation of actual building change regions. Finally, an edge graph perception module integrates edge information with the fused features, leveraging the spatial similarity of graph structures and the interaction of edge features to suppress irrelevant edge interference, thereby improving the model's sensitivity and accuracy in detecting subtle building changes. In experiments, DGFEG was tested on real-world change scenarios and multiple RSCD datasets. The results demonstrate its superior performance compared to existing state-of-the-art methods, proving its excellence and broad application potential in tackling complex BCD tasks.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3581-3598"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10829681","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Land Use Mapping of the Guangdong–Hong Kong Macao Greater Bay Area Based on a New Approach at 30 m Resolution for the Years 1976 to 2020","authors":"Yu Gu;Yangbo Chen;Jun Liu","doi":"10.1109/JSTARS.2024.3523707","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3523707","url":null,"abstract":"Multicategory land use data of high spatiotemporal resolution and large scale are crucial for studying regional ecological and environmental changes and urbanization impacts as well as for sustainable development planning. Currently available public data products include those of high spatial resolution global land use temporally limited to a single or short period, or global annual land cover products in which only a single land use type is depicted, such that regional characteristics are overlooked. In either case, fine-scale annual variation over longer time spans may not be reflected. In this study, the Google Earth Engine platform, Landsat satellite imagery, and a substantial number of manually interpreted samples were used to develop a dataset of annual land use changes in the Guangdong–Hong Kong Macao Greater Bay Area (GBA) at a 30 m resolution for the years 1976 to 2020. This dataset, termed Annual Land Use/Cover of the Greater Bay Area (LUC-GBA), was used to analyze the annual land use variation in 11 cities within the GBA. The high level of accuracy achieved with the LUC-GBA dataset was evidenced by an overall accuracy (OA) of 93.9% in 2020. The OA of interannual classification models ranged from 83.9% to 93.9%, and the kappa coefficients from 0.805 to 0.923. These results indicate that the LUC-GBA dataset effectively reflects the surface cover distribution and interannual dynamic evolution of the land area in the GBA at a 30 m spatial resolution, thus providing reliable data support for land surface process research and related applications.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3943-3958"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10827814","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ER-GMMD: Cross-Scene Remote Sensing Classification Method of Tamarix chinensis in the Yellow River Estuary","authors":"Liying Zhu;Yabin Hu;Guangbo Ren;Na Qiao;Ziyue Meng;Jianbu Wang;Yajie Zhao;Shibao Li;Yi Ma","doi":"10.1109/JSTARS.2024.3523346","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3523346","url":null,"abstract":"<italic>Tamarix chinensis</i> effectively prevents coastal erosion, stabilizes the surface of coastal wetlands, and improves the soil quality of saline-alkali land, playing a crucial role in coastal wetland ecosystem restoration. <italic>Tamarix chinensis</i> exhibits a wide distribution that is difficult to capture within a single remote sensing image, while its frequent interspersion with other vegetation results in significant intermixing. The characteristics of mixed <italic>tamarix chinensis</i> vary substantially across remote sensing images from different scenarios, and spectral confusion further complicates the process. These factors hinder the extraction and alignment of mixed <italic>tamarix chinensis</i> features during classification, resulting in low cross-scene classification accuracy. To address these challenges, this study proposes a deep learning-based cross-domain classification model, ER-GMMD, which leverages features extracted by deep residual networks for different mixed-growth patterns of <italic>tamarix chinensis,</i> and integrates dual feature alignment to address the cross-scene classification challenges of mixed-species <italic>tamarix chinensis</i>. Utilizing GF remote sensing images covering the <italic>tamarix chinensis</i> research area in the Yellow River Delta, along with field survey data, the model achieves precise classification of different mixed <italic>tamarix chinensis</i> types. Key results include: 1) The proposed model, trained with only 5% of the source domain samples, achieves an overall classification accuracy of 96.52% on the target domain samples, which is a 17.61% improvement compared with the traditional network U-Net without domain adaptation. 2) Compared with domain adaptation algorithms DAN and S-DMM, the proposed ER-GMMD model demonstrates higher accuracy on the constructed dataset, indicating its potential for high-precision classification of mixed vegetation in coastal wetlands.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"4305-4317"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10829769","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network","authors":"Zhe Zhao;Boya Zhao;Yuanfeng Wu;Zutian He;Lianru Gao","doi":"10.1109/JSTARS.2025.3525709","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3525709","url":null,"abstract":"Automatically extracting buildings with high precision from remote sensing images is crucial for various applications. Due to their distinct imaging modalities and complementary characteristics, optical and synthetic aperture radar (SAR) images serve as primary data sources for this task. We propose a novel boundary-link multimodal fusion network for joint semantic segmentation to leverage the information in these images. An initial building extraction result is obtained from the multimodal fusion network, followed by refinement using building boundaries. The model achieves high-precision building delineation by leveraging building boundary and semantic information from optical and SAR images. It distinguishes buildings from the background in complex environments, such as dense urban areas or regions with mixed vegetation, particularly when small buildings lack distinct texture or color features. We conducted experiments using the MSAW dataset (RGB-NIR and SAR data) and DFC track2 datasets (RGB and SAR data). The results indicate that our model significantly enhances extraction accuracy and improves building boundary delineation. The intersection over union metric is 2.5% to 3.5% higher than that of other multimodal joint segmentation methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3864-3878"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10824925","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data","authors":"Yu Li;Zifeng Yuan;Sarah Mazhar;Zhiguo Meng;Yuanzhi Zhang;Jinsong Ping;Ferdinando Nunziata","doi":"10.1109/JSTARS.2025.3525797","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3525797","url":null,"abstract":"Research on lunar oxides abundance has been spotlighted for its great significance in reconstructing the evolutionary history of the moon. In recent years, artificial intelligence technologies have been introduced to map oxides abundance on the lunar surface for their reliability and robustness. However, there are still some shortcomings in existing studies. First, the majority of these studies rely on spectral data and used in situ (drilled) ground truth samples collected by satellite missions. The detection depth of spectral sensors and the drilled depths of the returned samples are not consistent, lowering the reliability of the results. Moreover, existing machine/deep learning models may not be suitable for processing the data acquired in lunar exploration. In this article, we propose a novel deep learning model named multifrequency brightness temperature feature fusion network (MFBTFF-Net) for processing Chang'e-2 lunar microwave sounder (CELMS) data and it exploits the thermal radiation features related to various drilling depths to acquire the global lunar oxide abundance maps. The experimental results demonstrated that the proposed MFBTFF-Net model can significantly improve the estimation precision of most lunar oxides. The proposed method achieved root-mean-square error indices of 1.4449, 1.4826, and 0.9824 (wt.%) on estimating Al₂O₃, FeO, and TiO₂, which outperformed the state-of-the-art models by at least 0.0674, 0.6217, and 0.0578, respectively. Furthermore, based on the proposed model, we generated a new set of lunar oxide abundance maps. Compared with the abundance maps derived from spectral data, some discoveries can be obtained due to the unique penetration depth-related information provided by Chang'e-2 CELMS data. This study demonstrates the large potential of Chang'e-2 CELMS as a powerful new tool to understand the vertical structures of the moon under the regolith.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3921-3942"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10824911","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TE23D: A Dataset for Earthquake Damage Assessment and Evaluation","authors":"Can Ekkazan;M. Elif Karsligil","doi":"10.1109/JSTARS.2025.3526088","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3526088","url":null,"abstract":"Natural disasters, particularly earthquakes, require rapid and accurate damage assessment for effective response and recovery. In this work, we present TE23D (Türkiye Earthquakes of 6 February 2023 Dataset) consisting of 1183 images and 2080 polygons labeled as damaged. The dataset was developed using the satellite images taken after the earthquakes occurred on 6 February 2023 in Türkiye, and the dataset was evaluated for benchmark results using various deep learning-based object detection techniques. Unlike many approaches that utilize both pre- and post-disaster imagery, TE23D focuses exclusively on post-earthquake images due to the lack of relevant pre-disaster data. This approach simplifies damage detection by directly labeling anomalies caused by the earthquake.To evaluate the dataset, state-of-the-art segmentation models, including BEiT, DPT, Mask R-CNN, MobileViT, U-Net, U-Net++, and SegFormer, were trained and benchmarked. SegFormer demonstrated superior performance, achieving 92.49% overall pixel accuracy and 74.45% intersection over union for the damaged class. These results confirm the effectiveness of focusing solely on post-event imagery for accurate damage detection.The findings emphasize the crucial role of high-quality, targeted datasets, such as TE23D in enhancing disaster response. By offering a focused benchmark, this dataset enables an efficient identification of damaged areas by earthquakes. This capability for rapid damage assessment is essential for prioritizing emergency response efforts and helping to save lives. While TE23D is tailored to the Türkiye earthquake, its methodology provides a scalable framework for addressing damage assessment in other disaster scenarios, highlighting the importance of well-curated datasets in improving the effectiveness of damage assessment.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3852-3863"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10824929","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced CyGNSS Soil Moisture Retrieval Validated by In-Situ Data in Argentina's Pampas","authors":"Javier Arellana;Francisco Grings;Mariano Franco","doi":"10.1109/JSTARS.2025.3526445","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3526445","url":null,"abstract":"Soil moisture (SM) retrieval using signals of opportunity based on specularly reflected signals has gained significant attention in the past two decades. Specifically, with the Cyclone Global Navigation Satellite System (CyGNSS), the reflected signal is often modeled in its simplest form, utilizing the Fresnel reflection coefficients for a semi-infinite dielectric medium corrected with an effective roughness parameter. Within this framework, for bare soils condition, only two parameters need to be inferred: the dielectric permittivity <inline-formula><tex-math>$varepsilon$</tex-math></inline-formula> (related to SM) and the effective roughness <inline-formula><tex-math>$sigma$</tex-math></inline-formula>. Although this approach is relatively simple, our results show that both the estimated dielectric constant and the modeled reflectivity consistently overestimate CyGNSS observations. To address these overestimations, we propose a model where the reflected signal is scattered by a medium comprising two layers: one with a finite thickness <inline-formula><tex-math>$d$</tex-math></inline-formula> and permittivity <inline-formula><tex-math>$varepsilon _{1}$</tex-math></inline-formula> and the other semi-infinite with permittivity <inline-formula><tex-math>$varepsilon _{2}$</tex-math></inline-formula>. We observe that both the in-situ measurements of <inline-formula><tex-math>$varepsilon _{1}$</tex-math></inline-formula> and the reflectivity reported by CyGNSS align with the optimal values obtained from the fit, resulting in a 73% reduction in root mean square error when compared to the traditional approach. To further enhance SM retrieval, we propose incorporating full polarimetric images from SAOCOM. This will allow us to combine the low revisit time of CyGNSS with the high spatial resolution offered by SAOCOM.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3728-3734"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10829697","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A High-Precision Real-Time PWV Grid Model for the China Region and Its Preliminary Performance in WRF Assimilation","authors":"Pengfei Xia;Biyan Chen;Ning Huang;Xin Xie;Qinglan Zhang","doi":"10.1109/JSTARS.2025.3525770","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3525770","url":null,"abstract":"Precipitable water vapor (PWV) is a key parameter in studying water vapor variations during severe weather phenomena. The high-quality PWV maps are also of significant value for monitoring and early warning of geological disasters, such as landslides and debris flows. This study presents a high-precision real-time PWV grid model for the China region, utilizing global navigation satellite system (GNSS) observations and surface meteorological data. The model addresses the limitations of existing PWV retrieval methods by incorporating an improved altitude correction model for pressure and temperature using ERA5 reanalysis data. The model achieves a spatial resolution of 0.5° × 0.5° and incorporates real-time updates for accurate monitoring of atmospheric moisture variations. The model's performance was evaluated using surface meteorological observations and compared with the HGPT2 model. Results showed that the new model outperforms HGPT2 in terms of accuracy, particularly in low-latitude regions. In addition, the model was successfully assimilated into the weather research and forecasting (WRF) model, significantly improving the accuracy of the initial atmospheric field for numerical weather prediction. This study demonstrates the potential of GNSS and surface meteorological data in constructing high-resolution, real-time PWV models. The developed model provides valuable insights into atmospheric moisture variations and enhances the accuracy of weather forecasting and climate research in the China region.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"3433-3447"},"PeriodicalIF":4.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10824939","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}