Multi-temporal surface water mapping with high-resolution elevation and image data through weakly supervised deep learning

By: , and 

Links

Abstract

Monitoring the extent of surface water features (hydrography), accurately storing them in databases, and representing them on topographic maps are essential for various applications such as navigation and policy-making for legislative boundaries and permitting. In this context, hydrographic data includes features that generally have water present or image data showing signs that water is forming a terrain channel, and which would be included in 1:24,000 or larger scale topographic maps. In addition, reliable hydrographic data play a critical role to help manage environmental risks such as droughts, floods, fires, and landslides, as well as monitoring biological resources and pollutants. Inaccuracies in hydrography data can lead to modelling inaccuracies, resulting in economic, social, and environmental risks. However, generating sufficiently accurate high-resolution (HR) hydrography and terrain data for these purposes remains a substantial challenge primarily because of complex surface water dynamics and data handling limitations.  

Publication type Conference Paper
Publication Subtype Conference Paper
Title Multi-temporal surface water mapping with high-resolution elevation and image data through weakly supervised deep learning
DOI 10.5194/ica-abs-10-275-2025
Volume 7
Issue 10
Publication Date December 15, 2025
Year Published 2025
Language English
Publisher International Cartographic Association
Contributing office(s) Center for Geospatial Information Science (CEGIS)
Description 275, 3 p.
Larger Work Type Book
Larger Work Subtype Conference publication
Larger Work Title Abstracts of the International Cartographic Association
Country United States
State Alaska
Additional publication details