Abstract: To reduce the damage caused by geological disasters to human beings, accurate monitoring of geological information in natural environment is of great significance. Based on the correlation between geological hazards and remote sensing technology, the study introduces the faster regions with convolutional neural network (Faster R-CNN) algorithm, further utilizes feature extraction network, modifies the training method and optimizes the algorithm, so that it can be applied to remote sensing technology to improve the speed and accuracy of geological hazards detection. Finally, the PASCAL VOC and COCO datasets are used for the experimental evaluation and demonstration of the proposed method model. The results show that when the GIOU value is 0.6, the detection accuracy reaches the best. In the algorithm comparison, the AP@0.5 value of the improved Faster R-CNN algorithm designed in the study reaches 59, proving that the algorithm is satisfactory in both speed and accuracy, and achieves the expected goal of target detection. Moreover, the Faster R-CNN algorithm can be effectively applied to satellite remote sensing technology to quickly detect geological information in natural environment and make early warning measures by judging its attribute transformation, thus reducing losses caused by geological changes.