Spatial similarity geological disaster prediction method based on feature subset coupling model

A technology for geological hazards and feature subsets, applied in prediction, character and pattern recognition, instruments, etc., can solve problems such as result interference, improvement of difficult model formulas, and improved robustness and accuracy

Pending Publication Date: 2021-05-18
武汉中地云申科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Through the above analysis, the problems and defects of the existing technology are: the prediction of the existing geological disaster prediction method is sensitive to environmental changes, and it is difficult to obtain an accurate and stable result
In addition, the existing technology cannot distinguish the factors that contribute to the occurrence of geological disasters, which will cause some interference to the results
[0005] The difficulty in solving the above problems and defects is as follows: the basic prediction method has been deduced for many years, and it is quite mature, so it is difficult to improve the robustness and accuracy from the model formula; at present, the research on the selection of geological disaster hazard factors at home and abroad is comparatively limited. It is difficult to provide sufficient reference, and only rely on limited data to derive appropriate and effective screening schemes

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Spatial similarity geological disaster prediction method based on feature subset coupling model
  • Spatial similarity geological disaster prediction method based on feature subset coupling model
  • Spatial similarity geological disaster prediction method based on feature subset coupling model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0120] The prediction of geological hazards based on this model includes the following steps:

[0121] (1) Extraction of disaster factors, including obtaining disaster-causing factors related to geological hazards from data such as topographic maps, meteorological maps, DEM, and land use data maps, and standardizing the obtained disaster-causing factors to make corresponding layer.

[0122] (2) Acquisition of disaster points. From the historical database of geological disasters in the target area, historical geological disaster points are obtained, including key data such as occurrence time, location, and scope of influence. After obtaining the disaster points, combine the geological disasters in step 1 Factor layer, make a matrix of disaster points, and make a map.

[0123] (3) Make the disaster points obtained in step 2 into training data, set the number of member classifiers and subspace dimensions, and generate feature subsets;

[0124] (4) In each feature subset, genera...

Embodiment 2

[0128] The specific implementation method of the spatial similarity geological hazard prediction based on the feature subset coupling model is as follows:

[0129] (1) Extracting disaster factors. Specifically, Arcgis software can be used to extract key disaster-causing factors, such as slope, aspect, fault, average rainfall, water system, etc., from the topographic map, DEM, weather map, etc. of the target area , after extraction, each factor needs to be normalized. For continuous factors, the following formula can be used for processing:

[0130]

[0131] where μ is the mean of the factor and σ is the standard deviation of the factor. For discrete factors, such as aspect, values ​​can be used instead of categories, such as 1 for true north. After normalization processing, continue to use Arcgis software for mapping to make a hazard map of the target area.

[0132] (2) Obtain the historical disaster data of the target area, select a sufficient number of disaster points t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of geological disaster prediction, and discloses a spatial similarity geological disaster prediction method based on a feature subset coupling model, and the method comprises the steps: obtaining disaster-inducing factors related to geological disasters, carrying out the standardization processing of the obtained disaster-inducing factors, and making a geological disaster factor layer; obtaining historical geological disaster points and related data, obtaining a disaster point matrix, and making a map; setting the number of member classifiers and subspace dimensions, and generating a feature subset. A logic model tree is generated for each generated feature subset, corresponding parameters are adjusted, the optimal training result of each subset is obtained through calculation, and model performance is judged; and a corresponding geological disaster sensitivity map is made, and geological disaster risk prediction is performed according to the geological disaster sensitivity map. According to the method, the influence of factors on the prediction result is reduced, and the prediction accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of geological disaster prediction, and in particular relates to a spatial similarity geological disaster prediction method based on a feature subset coupling model. Background technique [0002] At present, geological disasters are characterized by strong destructive power, strong suddenness, and difficult prevention, which cause a large number of casualties and huge property losses to China every year, so the prediction of geological disasters is imminent. Since the last century, a variety of research methods have been used in the prediction of geological hazards. The most popular is the expert scoring model, which is a qualitative model based on the experience and knowledge of experts to evaluate the contribution of each geological environmental factor to the occurrence of geological disasters, and then calculate the possibility of geological disasters in the target area. The disadvantage of this method i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06K9/62G06Q50/26
CPCG06Q10/04G06Q50/26G06F18/241G06F18/214
Inventor 罗显刚林霏开朱双徐战亚李沦王钰莹周立博胡国丰卢爽
Owner 武汉中地云申科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap