Active-Passive Surface Water Classification: A New Method for High-Resolution Monitoring of Surface Water Dynamics

Abstract

This study develops a new, highly efficient method to produce accurate, high-resolution surface water maps. The “active-passive surface water classification” method leverages cloud-based computing resources and machine learning techniques to merge Sentinel 1 synthetic aperture radar and Landsat observations and generate monthly 10-m-resolution water body maps. The skill of the active-passive surface water classification method is demonstrated by mapping surface water change over the Awash River basin in Ethiopia during the 2015 East African regional drought and 2016 localized flood events. Errors of omission (water incorrectly classified as nonwater) and commission (nonwater incorrectly classified as water) in the case study area are 7.16% and 1.91%, respectively. The case study demonstrates the method's ability to generate accurate, high-resolution water body maps depicting surface water dynamics in data-sparse regions. The developed technique will facilitate better monitoring and understanding of the impact of environmental change and climate extremes on global freshwater ecosystems.