基于地理环境最优相似性约束的滑坡易发性评价方法
By quantifying and dynamically filtering similarity metrics in a multidimensional landslide hazard feature space, 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 hazard assessments, and achieves a more accurate and stable landslide hazard assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA HYDROELECTRIC ENGINEERING CONSULTING GROUP CHENGDU RESEARCH HYDROELECTRIC INVESTIGATION DESIGN AND INSTITUTE
- Filing Date
- 2026-05-09
- Publication Date
- 2026-07-17
AI Technical Summary
The existing landslide susceptibility assessment suffers from problems such as the reliance on spatial geometry/single topographic indicators for negative sample selection, which leads to the mixing of positive and negative sample features, low model identification accuracy, and poor robustness of evaluation results.
The landslide susceptibility assessment method based on the optimal similarity constraint of the geographical environment quantifies the similarity of the multidimensional disaster-causing feature space, adopts nested cross-validation and dynamic similarity ratio iterative optimization, eliminates false negative samples, constructs a high-quality training set, and improves the model's identification accuracy and the stability of the evaluation results.
It effectively eliminates the data pollution of the prediction model caused by false negative samples, greatly suppresses the prediction variance caused by feature redundancy and random noise, improves the identification accuracy of high-risk boundaries and the robustness of the evaluation system, and realizes the objective quantitative mapping of the global safety probability.
Smart Images
Figure CN122155443B_ABST