A Visualization Method for Data of InSAR Geological Subsidence Risk

Conference: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
12/17/2021 - 12/19/2021 at Shenyang, China

Proceedings: ICMLCA 2021

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Liu, Chenxu; Fan, Yue; Shao, Yongheng (Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang, Liaoning, China & University of Chinese Academy of Sciences, Beijing, China)
Lu, Ming (Infrastructure & Cloud Service, SSG, Lenovo, Beijing, China & University of Chinese Academy of Sciences, Beijing, China)
Dong, Zengshou (School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan Shanxi, China)

Abstract:
The ground deformation problem caused by excessive exploitation of underground resources is very prominent in our country. Nowadays, InSAR technology has become an important tool for monitoring ground deformation. In this paper, we process regular hexagonal resampling for InSAR ground subsidence data, use the cumulative amount of risk measurement points as the clustering index, and use the DBSCAN algorithm to realize the risk area division.DBSCAN clustering based on regular hexagonal resampling is not restricted, and the parameters of the DBSCAN algorithm are difficult to choose, both with high flexibility. This experiment compares the speed of presentation with the effect of partitioning, and the results show that our method of region division is more intuitive. The results can be displayed within millisecond response, and the presentation speed is 1297.5 times faster than direct on-page plotting. Our method has a high practical application value for InSAR geological subsidence data.