Water body detection of South Dongting Lake based on remote sensing images from 2018 to 2022

Water body detection plays an important role in the field of ecological research, but efficient, accurate and automatic long-time water body detection methods still need to be explored. Therefore, this paper proposes a water body detection method based on Google earth engine, which is based on the automatic threshold recognition principle of the OTSU method, and conducts automatic water detection of a total of 135 Sentinel-1 images of South Dongting Lake from 2018 to 2022. The study shows that the overall classification accuracy of the method is 92.61%, and the Kappa coefficient is 0.86, and the results reflect the impact of extreme climate change on the seasonal water distribution of South Dongting Lake.