Deep Learning-Based Classification of Aquatic Vegetation Using GF-1/6 WFV and HJ-2 CCD Satellite Data
Rattachement africain : cn. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
The Yangtze River Basin, one of China’s most vital watersheds, sustains both ecological balance and human livelihoods through its extensive lake systems. However, since the 1980s, these lakes have experienced significant ecological degradation, particularly in terms of aquatic vegetation decline. To acquire reliable aquatic vegetation data during the peak growing season (July–September), when clear-sky conditions are scarce, we employed Chinese domestic satellite imagery—Gaofen-1/6 (GF-1/6) Wide Field of View (WFV) and Huanjing-2A/B (HJ-2A/B) Charge-Coupled Device (CCD)—with approximately one-day revisit frequency after constellation networking, 16 m spatial resolution, and excellent spectral consistency, in combination with deep learning algorithms, to monitor aquatic vegetation across the basin. Comparative experiments identified the near-infrared, red, and green bands as the most informative input features, with an optimal input size of 256 × 256. Through visual interpretation and dataset augmentation, we generated a total of 5016 labeled image pairs of this size. The U-Net++ model, equipped with an EfficientNet-B5 backbone, achieved robust performance with an mIoU of 90.16% and an mPA of 95.27% on the validation dataset. On independent test data, the model reached an mIoU of 79.10% and an mPA of 86.42%. Field-based assessment yielded an overall accuracy (OA) of 75.25%, confirming the reliability of the model. As a case study, the proposed model was applied to satellite imagery of Lake Taihu captured during the peak growing season of aquatic vegetation (July–September) from 2020 to 2025. Overall, this study introduces an automated classification approach for aquatic vegetation using 16 m resolution Chinese domestic satellite imagery and deep learning, providing a reliable framework for large-scale monitoring of aquatic vegetation across lakes in the Yangtze River Basin during their peak growth period.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Deep Learning-Based Classification of Aquatic Vegetation Using GF-1/6 WFV and HJ-2 CCD Satellite Data
- Date Crossref
- 25/11/2025
- Éditeur
- MDPI AG
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
Chinese Academy of Sciences pays non établi dans la noticeOrganisme public
-
Beijing Institute of Big Data Research pays non établi dans la noticeStructure de recherche
-
Aerospace Information Research Institute pays non établi dans la noticeUniversité ou école supérieure
-
University of Chinese Academy of Sciences pays non établi dans la noticeUniversité ou école supérieure
-
International Research Center of Big Data for Sustainable Development Goals pays non établi dans la noticeOrganisation à but non lucratif
-
Satellite Application Center for Ecology and Environment pays non établi dans la noticeOrganisme public
-
Tiandi Science & Technology (China) pays non établi dans la noticeEntreprise
-
Beijing Normal University pays non établi dans la noticeUniversité ou école supérieure
-
Capital Normal University Beijing Laboratory of Water Resource Security pays non établi dans la noticeUniversité ou école supérieure
-
Key Laboratory of Digital Earth Science pays non établi dans la noticeStructure de recherche
-
Ltd. Jiangsu Tianyan Environment Technology Co. pays non établi dans la noticeEntreprise
-
College of Resources Environment and Tourism pays non établi dans la noticeUniversité ou école supérieure
Chinese Academy of Sciences, Beijing Institute of Big Data Research et Aerospace Information Research Institute, avec 9 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.