Fine-Grained Classification of Lakeshore Wetland–Cropland Mosaics via Multimodal RS Data Fusion and Weakly Supervised Learning: A Case Study of Bosten Lake, China
Zhang J. Samat A. Li E. Zhu E. Li W.
January 2026Multidisciplinary Digital Publishing Institute (MDPI)
Land
2026#15Issue 1
High-precision monitoring of arid wetlands is vital for ecological conservation, yet traditional methods incur prohibitive labeling costs due to complex features. In this study, the wetland of Bosten Lake in Xinjiang is selected as a case area, where Pleiades and PlanetScope-3 multimodal remote sensing data are fused using the Gram–Schmidt method to generate imagery with high spatial and spectral resolution. Based on this dataset, we systematically compare the performance of fully supervised models (FCN, U-Net, DeepLabV3+, and SegFormer) with a weakly supervised learning model, One Model Is Enough (OME), for classifying 19 wetland–cropland mosaic types. Results demonstrate that: (1) SegFormer achieved the best overall performance (98.75% accuracy, 95.33% mIoU), leveraging its attention mechanism to enhance semantic understanding of complex scenes. (2) The weakly supervised OME, using only image-level labels, matched fully supervised performance (98.76% accuracy, 92.82% F1-score) while drastically reducing labeling effort. (3) Multimodal fusion boosted all models’ accuracy, most notably increasing U-Net’s mIoU by 63.39%. (4) Models exhibited complementary strengths: U-Net excelled in wetland vegetation segmentation, DeepLabV3+ in crop classification, and OME in preserving spatial details. This study validates a pathway integrating multimodal fusion with WSL to balance high accuracy and low labeling costs for arid wetland mapping.
multimodal data fusion , PlanetScope-3 , Pleiades , semantic segmentation , weakly supervised learning , wetland classification
Text of the article Перейти на текст статьи
State Key Laboratory of Ecological Safety and Sustainable Development in Arid Lands, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi, 830011, China
University of Chinese Academy of Sciences, Beijing, 100049, China
China-Kazakhstan Joint Laboratory for Remote Sensing Technology and Application, Al-Farabi Kazakh National University, Almaty, 050012, Kazakhstan
Key Laboratory of RS & GIS Application Xinjiang, Urumqi, 830011, China
School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou, 221116, China
Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, 27100, Italy
State Key Laboratory of Ecological Safety and Sustainable Development in Arid Lands
University of Chinese Academy of Sciences
China-Kazakhstan Joint Laboratory for Remote Sensing Technology and Application
Key Laboratory of RS & GIS Application Xinjiang
School of Geography
Department of Electrical
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026