Landslide susceptibility evaluation method, system, device and computer readable storage medium

By determining the deformation rate and disaster-prone environmental characteristic factors, and combining them with an automatic optimization machine learning model, the real-time data of landslide susceptibility assessment results and environmental characteristics were deeply integrated. This solved the problem of insufficient accuracy of assessment results in existing technologies and improved the accuracy and timeliness of landslide susceptibility prediction.

CN122196461APending Publication Date: 2026-06-12SANXIA JINSHAJIANG YUNCHUAN HYDROPOWER DEV CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SANXIA JINSHAJIANG YUNCHUAN HYDROPOWER DEV CO LTD
Filing Date
2026-05-15
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

In existing technologies, surface deformation data identified by InSAR is only used as a post-approval means for landslide susceptibility assessment. It lacks deep integration with machine learning models, resulting in insufficient accuracy in reflecting the real-time activity status of slopes.

Method used

By determining the deformation rate based on the design matrix and target vector, and combining the disaster-prone environmental characteristic factors and deformation rate to determine the target feature subset, the results of landslide susceptibility assessment are obtained by inputting the automatic optimization machine learning model for forward propagation and node splitting calculation, thus achieving deep integration of real-time deformation data and environmental characteristics.

Benefits of technology

It significantly improves the accuracy and reliability of landslide susceptibility assessment, enabling the assessment results to reflect the current activity state of the slope and enhancing the timeliness and accuracy of prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122196461A_ABST
    Figure CN122196461A_ABST
Patent Text Reader

Abstract

The application discloses a landslide susceptibility evaluation method, system and device and a computer readable storage medium, relates to the field of geological disaster risk assessment, and specifically comprises the following steps: determining a deformation rate based on a design matrix and a target vector, wherein the design matrix is a small baseline network matrix formed by time intervals corresponding to interferograms, and the target vector is a column vector corresponding to unwrapped interferometric phase and comprising slope displacement information; determining a target feature subset according to a disaster-forming environment characteristic factor and the deformation rate; inputting the target feature subset into a preset automatic optimization machine learning model to perform forward propagation and node splitting calculation, so as to obtain a preliminary probability value of landslide occurrence of a slope unit; and determining a landslide susceptibility evaluation result based on the preliminary probability value and the deformation rate. The application can improve the accuracy of the landslide susceptibility evaluation result.
Need to check novelty before this filing date? Find Prior Art