The invention discloses a hyperspectral remote sensing image classification method based on a combination of six-layer convolutional neural network and spectral-spatial information, which selects hyperspectral remote sensing image data of a certain number of bands, and performs spatial analysis on the selected two-dimensional image data of each band. Mean filtering, and then convert the format of the multi-band data corresponding to each pixel, and convert the one-dimensional vector into a square matrix, that is, each pixel corresponds to a square matrix data. Then design a six-layer classifier based on deep learning template, including input layer, first convolutional layer, maximum pooling layer, second convolutional layer, fully connected layer, output layer; extract the square matrix corresponding to several pixels The data is used as the training set, input the classifier and train the classifier; extract the square matrix data corresponding to several pixels as the test set, input it into the trained classifier, observe the classification results output by the trainer, and compare with the real The classification information is compared to verify the performance of the classifier. The classification accuracy rate of the present invention is higher than the existing 5-CNN method.