Landslide Disaster Prediction Method Based on Improved Bayesian Network

A Bayesian network and prediction method technology, applied in the field of landslide disaster prediction based on the improved Bayesian network, can solve the problems of low error tolerance rate and low accuracy of the algorithm, and achieve the goal of improving the network fault tolerance rate and forecasting accuracy Effect
CN109146144BActive Publication Date: 2021-11-19XI'AN POLYTECHNIC UNIVERSITY
3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XI'AN POLYTECHNIC UNIVERSITY
Publication Date
2021-11-19

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The landslide disaster prediction method based on the improved Bayesian network disclosed by the present invention first establishes a landslide body monitoring and early warning system, obtains the initial landslide disaster impact factor data, and uses the PCA algorithm to extract and screen out the main impact factors after standardized processing; the screened out The main influencing factors of the sample data are divided into training sample set and test sample set in proportion, and the landslide occurrence level is divided; then the landslide prediction model based on the improved Bayesian is constructed, and the landslide occurrence probability after introducing the feature quantity is calculated by weighting , and add a closed-loop learning process to complete the prediction of landslide disasters; the method disclosed in the present invention screens the main influencing factors of landslide disasters, weights the feature quantities based on the improved Bayesian model, and adds a closed-loop learning link to output landslide occurrence probability, increasing fault tolerance rate to improve forecast accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of geological disaster prediction methods, and relates to a landslide disaster prediction method based on an improved Bayesian network. Background technique

[0002] Landslide is an important type of geological disaster, which has a great impact on regional transportation, power stations, factories and mines, urban and rural construction, etc., and seriously threatens people's lives and property safety. The occurrence of landslides is affected by multiple factors, and how to predict the possibility of landslides in advance through the influencing factors has become the focus of attention.

[0003] In view of the characteristics of high frequency of landslide disasters and wide range of influence, domestic scholars have used different methods to predict landslide disasters in recent years, but there are still certain limitations. For example, the neural network model has good self-learning and fault-tolerant...

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