Landslide susceptibility evaluation method based on sample automatic selection and earth surface deformation rate

Abstract

The invention discloses a landslide susceptibility evaluation method based on sample automatic selection and earth surface deformation rate, comprising the following steps: extracting evaluation factors to obtain earth surface deformation rate; automatically selecting landslide samples and non-landslide samples in different periods; performing normalization processing on the evaluation factors by using the selected landslide sample; training an sDAE-RF model by using the landslide sample and the non-landslide sample to obtain a landslide susceptibility initial probability; and correcting the initial probability of the landslide susceptibility by using the surface deformation rate to obtain a landslide susceptibility evaluation partition map. According to the method, the surface deformation rate reflecting the landslide motion state is utilized, so that the evaluation result is more consistent with the actual distribution condition of the regional landslide, the accuracy and practicability of the evaluation method are improved, and accurate decision data are provided for subsequent landslide disaster risk management.

Description

technical field [0001] The invention belongs to the technical field of landslide disaster prediction, in particular to a landslide susceptibility evaluation method based on automatic sample selection and surface deformation rate. Background technique [0002] Landslide disaster is one of the geological disasters with wide distribution, great impact and serious damage in the world. According to incomplete statistics, the areas that have been threatened by landslide disasters and may be threatened by landslides account for about 1 / 5 to 1 / 4 of the country's land area, and the property losses caused by landslide geological disasters exceed 1 billion yuan per year. Therefore, it is very important to carry out scientific and effective risk management for landslide disasters. [0003] Landslide disaster susceptibility evaluation is to predict the spatial and temporal distribution and occurrence probability of landslide disasters, which can provide important decision-making basis f...

AI Technical Summary

Problems solved by technology

However, most of the current landslide samples are interpreted based on historical data and optical remote sensing images. The selection of samples depends on manual experience and the work efficiency is low.

Moreover, the period of landslide samples obtained is relatively single, and most of them are new landslides in recent years. It is difficult to obtain samples of unstable potential landslide areas, which makes it difficult for subsequent evaluation methods based on machine learning to fully reflect the actual situation of the area.

Images