FY-3D/MERSI Global Surface Water Extraction Based on DNN Method

The acquisition of surface water information is of great significance of the study of global change. In this study, the Koppen climate zone was firstly used to select sample data onto different climate zones around the world, and then water and non-water samples were collected for each sample. Get as complete a sample of information as possible worldwide. Deep Neural Networks method is adopted to improve the model building, The features data is FY3D/MERSI, containing 6 bands 250m resolution data, add the NDVI and EVI to enhance characteristic data, use the attention mechanism to enhance the model, to strengthen the adaptability for different regions, the model for predicting data using global standardization process. The results show that this method can effectively extract the information on land surface water, especially for different disturbance conditions such as cloud and shadow under cloud. Water tests for 33 different regions of the world show that the method of sample set and model can adapt to different regions of the world.