Article citationsMore>>

Huang, F., Zhang, J., Zhou, C., Wang, Y., Huang, J., & Zhu, L. (2020). A Deep Learning Algorithm Using a Fully Connected Sparse Auto Encoder Neural Network for Landslide Susceptibility Prediction. Landslides, 17, 217-229. https://doi.org/10.1007/s10346-019-01274-9

has been cited by the following article:

• TITLE: Evaluation of the Collapse Susceptibility of the Northern Foot of the Tianshan Mountains

  AUTHORS: Zhenya Chen, Jie Tang, Wei Huang, Baoying Ye

  KEYWORDS: Tianshan Mountain, Collapse, Susceptibility, Frequency Ratio

  JOURNAL NAME: Journal of Geoscience and Environment Protection, Vol.10 No.4, April 29, 2022

  ABSTRACT: Collapse is a geological disaster second only to landslides and occurs in large numbers every year in the northern foothills of the Tianshan Mountains in Xinjiang, China. We collected a variety of data such as topography, geological vegetation coverage, and human activities, and used spatial correlation analysis to eliminate factors with strong correlations. The frequency of collapse was calculated by the frequency ratio method and a hierarchical map was made. The result shows, in low susceptibility zone (LSI = 0 - 4), only 3 collapses happened, and 0.39% of total collapses. In middle susceptibility zone (LSI = 4 - 7.5), 35 collapses happened, and 5.66% of total collapses. In high susceptibility zone (LSI = 7.5 - 10), 64 collapses happened, and 10.36% of total collapses. In extremely high susceptibility zone (LSI = 10 - 14), 516 collapses happened, and 83.5% of total collapses. Using the GIS-based frequency method, the susceptibility to collapse was calculated and mapped, which was in good agreement with the actual landslide data. Collapse susceptibility results provide guidance for engineering construction.