Analysis of Radar Technology Identification Model for Potential Geologic Hazard based on Convolutional Neural Network and Big Data

Abstract

To ensure the proper adoption of new technologies in identifying the potential geologic hazard on tourist routes, convolutional neural network (CNN) technology is applied in the radar image geologic hazard information extraction. A scientific and practical geologic hazard radar identification model is built, which is based on CNN’s image identification and big data algorithm calculation, and it can effectively improve the geologic hazard identification accuracy. By designing experiments, the geologic hazard radar image data are verified, and the practicality of radar image intelligent Identification under CNN and big data technology is also verified. The results show that the images of different resolution sizes all play a significant role in identification of geologic hazard performed by CNN. However, there are differences in the performance of different CNN models. With the continuous increase of training samples, the identification accuracy of various network models is also improved. By means of radar image test, the identification capability of CNN model is the best, the highest precision is 93.61%, and the geologic hazard recall rate is 98.27%. Apriori algorithm is introduced into data processing, and the running speed and efficiency of identification models are improved, with favorable identification effect in variable data sets. This research can provide theoretical ideas and practical value for the development of potential geologic hazard identification on tourist routes.

Landslide Hazard Identification Based on Deep Learning and Sentinel-2 Remote Sensing Imagery

“…Common convolutional neural network models used for image classification include: AlexNet, VGG, ResNet, DenseNet, UNet, and GoogLeNet, etc. [6][7][8] , combined with multi-source remote sensing data, terrain and geological data, and applied to landslide image detection, which can Improve the accuracy of landslide identification and improve the efficiency of landslide detection [9][10][11][12] .…”