HISEA -1 SAR Floodwater Mapping Dataset

The dataset can be used for deep learning of flood water extraction. They are generated from 20 HISEA-1 images of  3 different flood events in 2021. All images are level-2 ORG products, striping mode, 3 m resolution, VV polarization.

These SAR images have been manually labeled to produce the water bodies dataset. All sample sets are randomly allocated in the ratio of 6:2:2, and divided into 1404 training sets, 468 validation sets, and 468 test sets (a total of 2340 experimental data). This dataset covers 20,000 square kilometers, and contains rivers, tributaries, reservoirs, lakes and paddy fields.