成果归属机构：

地理科学学部

作者：

Xu,Haojun¹ ;Wu,Jianjun(武建军) ^1,2 ;Yao,Jiaqi¹ ;Xu,Nan³ ;Mo,Fan⁴ ;Li,Teng⁵ ;Lu,Qingkai¹ ;Xia,Haobin^1,2 ;Zhang,Jianhang⁶ ;Wang,Yuhao⁷

单位：

[1]Tianjin Normal Univ, Acad Ecol Civilizat Dev JING JIN JI Megalopolis, Tianjin, Peoples R China;[2]Beijing Normal Univ, Fac Geog Sci, Beijing, Peoples R China;[3]Shenzhen Univ, Sch Architecture & Urban Planning, Shenzhen, Peoples R China;[4]Minist Nat Resources, Land Satellite Remote Sensing Applicat Ctr, Beijing, Peoples R China;[5]Sun Yat Sen Univ, Sch Geospatial Engn & Sci, Zhuhai, Peoples R China;[6]Univ Tokyo, Res Ctr Adv Sci & Technol, Meguro, Tokyo, Japan;[7]Hohai Univ, Sch Earth Sci & Engn, Nanjing, Peoples R China

关键词：

SURFACE-WATER; INDEX NDWI; MISSION

摘要：

Accurately delineating inland water bodies and monitoring surface water dynamics are crucial for hydrological research and climate adaptation. Surface water and ocean topography (SWOT) satellites has significantly improved global surface water observation capabilities. However, in complex inland environments, SWOT data are often affected by stripe noise and quality control (QC) marker failures, which can easily lead to water body extraction errors or the omission of narrow water bodies. To address these issues, we developed SDNet, a transformer-based multi-scale framework. This design suppresses high-frequency stripe noise while preserving fine-scale hydrological boundaries, thus significantly improving the reliability of water body extraction. Experimental results for different water bodies show that: (1) SDNet achieved high accuracy across water bodies of different scales. Compared to the QC-based classification, the Water Body Intersection Rate (WIR) and Background Intersection Rate (BIR) of our method increased by 23.68% and 45.96%, respectively, for large water bodies. WIR further increased by 2.83% for medium-scale water bodies and by a factor of 3.57 for small water bodies. (2) Cross-validation using ICESat-2 altimetry data showed that the SWOT altimetry error was positively correlated with cross-track distance. The median errors ranged from 0.117 m to 0.181 m at 100 m resolution and 0.111 m to 0.170 m at 250 m resolution, with the mean absolute error remaining in the sub-meter range. (3) Seasonal hydrological analysis revealed distinct response patterns across different water body types to water level changes. Natural lakes are mainly driven by climate processes, while controlled reservoirs exhibit multi-peak dynamic characteristics dominated by human regulation. These findings provide a scalable solution for multi-scale water body monitoring, contributing valuable support to hydrological research, flood risk assessment, and climate adaptation strategies.

基金：

Shenzhen Key Laboratory Programme [SYSPG20241211173845013]; Key Laboratory of Land Satellite Remote Sensing Application, Ministry of Natural Resources of the People's Republic of China [KLSMNR-K202309]; the Natural Science Foundation of Jiangsu Province [BK20240258]; the National Key Research and Development Programme of China [2024YFF0617900]; National Natural Science Foundation of China [42101343 and 42001416]; Open-end Funds of Ministry of Education Key Laboratory for Earth System Modelling (Tsinghua University) [and the Disciplines Breakthrough Project in Aerospace Information and Spatiotemporal Intelligence, MOE, China.]; Jiangsu Marine Science and Technology Innovation Project [JSZRHYKJ202302]; the State Key Laboratory of Micro-Spacecraft Rapid Design and Intelligent Cluster [MS01240105]

语种：

英文

DOI：

10.1080/15481603.2026.2636315

来源：

GISCIENCE & REMOTE SENSING,2026(1):.

出版日期：

2026-12-31

提交日期：

2026-03-18

引用参考：

Xu,Haojun;Wu,Jianjun;Yao,Jiaqi;Xu,Nan;Mo,Fan;Li,Teng;Lu,Qingkai;Xia,Haobin;Zhang,Jianhang;Wang,Yuhao. SDNet: a multi-scale SWOT framework for denoising and quality-control optimization in inland water body extraction[J]. GISCIENCE & REMOTE SENSING,2026(1):.