The article developed a technique for using convolutional neural networks for automatic segmentation of rural roads using satellite images. The analysis of the subject area and the relevance of this study. The development of a neural network based on U-net was carried out in Python 3x using the libraries TensorFlow, TensorBoard, Pandas, Numpy, Scipy, Matplotlib, Sklearn. The neural network was trained on a training sample of 880 images prepared by hand marking. The accuracy of the developed model when testing on prepared samples was 64%. According to the results of the study, conclusions were drawn and prospects for further functional development of the developed tools were determined.