Landslide susceptibility assessment method based on optimal similarity constraint of geographical environment

By quantifying similarity in a multidimensional landslide-prone feature space and using nested cross-validation, false negative samples are eliminated, and a high-quality training set is constructed. This solves the problems of low model identification accuracy and poor robustness in existing landslide susceptibility assessments, and improves the accuracy and stability of landslide susceptibility assessments.

CN122155443AActive Publication Date: 2026-06-05CHINA HYDROELECTRIC ENGINEERING CONSULTING GROUP CHENGDU RESEARCH HYDROELECTRIC INVESTIGATION DESIGN AND INSTITUTE
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA HYDROELECTRIC ENGINEERING CONSULTING GROUP CHENGDU RESEARCH HYDROELECTRIC INVESTIGATION DESIGN AND INSTITUTE
Filing Date
2026-05-09
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

In existing landslide susceptibility assessments, the selection of negative samples relies on spatial geometry/single topographic indicators, resulting in overlapping positive and negative sample features, low model identification accuracy, and poor robustness of assessment results.

Method used

The landslide susceptibility assessment method based on the optimal similarity constraint of the geographical environment eliminates false negative samples by quantifying the similarity of the multidimensional disaster-causing feature space, and constructs a high-quality training set by using nested cross-validation iterative optimization to improve the model's identification accuracy and robustness.

Benefits of technology

It effectively eliminates the data pollution of the prediction model caused by false negative samples, suppresses the prediction variance caused by feature redundancy and noise, and improves the identification accuracy of high-risk boundaries and the stability of evaluation results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122155443A_ABST
    Figure CN122155443A_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of geological disaster risk assessment, and discloses a landslide susceptibility evaluation method based on optimal similarity constraint of geographical environment, which solves the problems of feature aliasing of positive and negative samples, low model recognition accuracy and poor robustness of evaluation results in the existing landslide susceptibility evaluation due to the dependence of negative sample selection on spatial geometry / single terrain index and the failure to remove positive sample noise. The present application scheme is summarized as follows: a multi-dimensional disaster-prone feature space is constructed by fusing multi-source geographic spatial data, and the multi-dimensional geographical environment comprehensive similarity of the calculation unit and the landslide point is calculated; the optimal representative observation benchmark is determined by nested cross-validation iteration optimization, the global landslide density is inversely inferred and mapped into non-landslide credibility; balanced negative samples are extracted in the high credibility safety area, and a machine learning model is trained to complete the evaluation. The present application can improve the model recognition accuracy and evaluation stability, and is suitable for regional landslide susceptibility evaluation in complex geological environment.
Need to check novelty before this filing date? Find Prior Art