Based on deep learning, a desertification grassland classification (DGC) and three-dimensional convolution neural network (3D-CNN) model is established. The F-norm(2) paradigm is used to reduce the data; the data volume was effectively reduced while ensuring the integrity of the spatial information. Through structure and parameter optimization, the accuracy of the model is further improved by 9.8%, with an overall recognition accuracy of the optimized model greater than 96.16%. Accordingly, high-precision classification of desert grassland features is achieved, informing continued grassland remote sensing research.