The shapefile contains 354 polygons which are boundaries of retrogressive thaw slumps (RTSs) and other land covers (non-RTS) in Beiluhe on the Tibetan Plateau for training a deep learning algorithm (DeepLabv3+). Among them, 264 are RTS boundaries delineated on Planet images acquired in May 2018, 90 of them are non-RTS polygons. In the attribute table of the shapefile, "class_int" equal to "1" means an RTS polygon and "0" for a non-RTS polygon.

Supplement to: Huang, Lingcao; Luo, Jing; Lin, Zhanju; Niu, Fujun; Liu, Lin (2020): Using deep learning to map retrogressive thaw slumps in the Beiluhe region (Tibetan Plateau) from CubeSat images. Remote Sensing of Environment, 237, 111534