 The study proposes a fully automatic classification tree approach to accurately quantify surface water extent in wetlands using sentinel, one synthetic aperture radar, SAR, data and training datasets derived from prior class masks. The proposed method reduces omission errors among water bodies by 10% and commission errors among non-water classes by 4% when compared with results generated using the shuttle radar topography mission, SRTM, water body dataset or composited dynamic surface water extent, CDSWE, class probabilities. The study finds that including prior water masks that reflect the dynamics in surface water extent is important for accurately mapping water bodies using SAR data. This article was authored by Wenli Huang, Ben DeVries, Qin Kuan Huang and others.