Active-Passive Water Classification Results over the Awash River Basin, Ethiopia for October 2014-March 2017

The “active-passive surface water classification” (APWC) method leverages cloud-based computing resources and machine learning techniques to merge Sentinel 1 synthetic aperture radar and Landsat observations and generate monthly 10-meter resolution waterbody maps. Merging data from two sensor types reduces the impact of errors associated with the individual sensors. The skill of the APWC method is demonstrated by mapping surface water change over the Awash River basin in Ethiopia from October 2014 through March 2017. This period corresponds to the 2015 East African regional drought and 2016 localized flood events. Errors of omission and commission in the case study area are 7.16% and 1.91%, respectively. These data were generated using the APWC method on August 18, 2017.