Geological disaster risk evaluation method, equipment, medium and product

CN120562880AActive Publication Date: 2025-08-29ZHEJIANG GEOLOGIC & MINERAL TECH
View PDF 6 Cites 6 Cited by

Patent Information

Application Number
CN202510755785.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-07
Publication Date
2025-08-29
Estimated Expiration
2045-06-07

AI Technical Summary

Technical Problem

In areas with scarce data, traditional geological disaster risk assessment methods cannot accurately assess disaster risks due to lack of sufficient data support.

Method used

The evaluation area is divided into data-intensive source domains and sparse target domains, and shared characteristics across regions are determined through principal component analysis. The domain-adversarial neural network containing gradient inversion layer is used for pre-training and adversarial training, and the target domain expansion data is generated and a cross-region adaptation model is constructed.

Benefits of technology

It effectively improves the accuracy and accuracy of geological disaster risk assessment in data scarce areas, and enhances the adaptability and generalization capabilities of the model in the target domain.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120562880A_ABST
    Figure CN120562880A_ABST
Patent Text Reader

Abstract

The invention discloses a geological disaster risk evaluation method, equipment, a medium and a product, and relates to the field of data processing. The method comprises the following steps: dividing an evaluated region into a source domain and a target domain according to the density of geological environment data; determining cross-regional shared features and performing dimension reduction and denoising optimization to obtain an optimized feature set; constructing a domain adversarial neural network containing a gradient inversion layer, and performing pre-training based on the source domain optimization feature set to obtain a source domain pre-training model; reversing a gradient direction through a gradient inversion layer in adversarial training, and reducing a feature distribution difference between a source domain and a target domain to obtain a cross-regional adaptation model; performing data expansion processing on the target domain optimization feature set by using the model to obtain target domain expansion data; and finally, performing geological disaster risk evaluation according to the target domain expansion data to obtain a geological disaster risk evaluation result of the target domain. According to the invention, the problem of insufficient evaluation precision caused by insufficient data volume in a data scarce region can be relieved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Sample-free reservoir area landslide susceptibility prediction method based on domain adaptive transfer learning

    CN115630336A

  • Far-field speech recognition method, system and device and storage medium

    CN117612515A

  • Geological disaster risk evaluation method and system based on machine learning

    CN118840829A

  • Fault diagnosis method based on sparse heterogeneous data collaboration, medium and product

    CN119179923A

  • GIS-based geological disaster monitoring point data expression method and system

    CN119961345A

Cited By

  • Geological disaster risk intelligent pre-judgment method based on deep learning

    CN121010228A

  • A geological disaster risk intelligent prediction method based on deep learning

    CN121010228B

  • YOLO-based avalanche monitoring self-improvement system and method

    CN121482659A

  • Avalanche monitoring self-perfecting system and method based on YOLO

    CN121482659B

  • Unbalanced disaster risk prediction method based on WGAN-CNN

    CN121766509A