Deep learning-based black and odorous water body remote sensing monitoring and grading method

The invention provides a black and odorous water body remote sensing monitoring grading method based on deep learning. The method comprises the following steps: acquiring a satellite remote sensing image of a research area; preprocessing the satellite remote sensing image, and extracting each water body region from the preprocessed satellite remote sensing image to obtain a plurality of water body region images; performing wave band combination and normalization processing on each water body region image to obtain a water body region multi-source image; and training the U-Net deep learning network model to obtain a trained U-Net deep learning network model. According to the method, a U-Net deep learning network model of combination of multiple indexes of ground sample data and satellite images is established through preprocessing of high-spatial-resolution satellite images, multiple index wavebands can be combined, and spatial distribution of clean water, mild black and odorous space distribution and severe b