Rainfall-type geological hazard warning and prediction model based on RBFN machine learning and a learning method

A technology of machine learning and geological disasters, applied in neural learning methods, biological neural network models, predictions, etc., can solve problems such as insufficient prediction accuracy of simple models, difficulty in obtaining, and complex models requiring many parameters, so as to facilitate promotion and implementation, The effect of small amount of model calculation

Inactive Publication Date: 2019-01-22
NANJING CENT CHINA GEOLOGICAL SURVEY
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] One of the purposes of the present invention is to address the above deficiencies and provide a RBFN machine learning-based rainfall-type geological disaster early warning and forecasting model, in order to expect to solve the subjective

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
  • Rainfall-type geological hazard warning and prediction model based on RBFN machine learning and a learning method
  • Rainfall-type geological hazard warning and prediction model based on RBFN machine learning and a learning method
  • Rainfall-type geological hazard warning and prediction model based on RBFN machine learning and a learning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further elaborated below in conjunction with the accompanying drawings.

[0045]As mentioned above, the invention proposes an RBFN-based rainfall-type geological disaster early warning and forecasting model. By introducing concepts such as continuous rainfall, soil rainfall index, RBFN value and CL contour, and using the machine learning algorithm of RBF kernel function, the In the past, the dimensionless hard threshold of rainfall was improved to the dimensionless soft threshold for early warning unit classification, which avoided the subjective factors assumed in the past statistical methods, and was applicable to the early warning and forecast of rainfall-type geological disasters in any region.

[0046] The technical method of the present invention mainly includes: the rainfall-type geological disaster early warning and forecasting model based on RBFN machine learning mainly includes the structure of RBFN (Radical Basis Function Network,...

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 discloses a rainfall-type geological hazard warning and prediction model based on RBFN machine learning and a learning method thereof, belonging to a geological hazard monitoring technology. The model comprises an input layer, a hidden layer and an output layer. The input layer is a vector X=(x1,x2), wherein x1 is soil raining amount indix and x2 is hour raining amount. The output layer is a scalar RBFN value; The hidden layer is composed of m radial basis functions. The unit of operation of an array composed of hidden layers is the node of the hidden layers, which contains a central vector c and has the same dimension as the parameter vector x of the input layer. With taking rainfall as the main inducement of disasters, rainfall and actual disasters as a priori events, a rainfall-type geological hazard early warning and prediction model is established. The RBFN model is used to classify the early warning units by introducing soil rainfall index and machine learning algorithm into dimensionless soft thresholds, which avoids the drawbacks of subjective and statistical methods in the past.

Description

technical field [0001] The present invention relates to a geological disaster monitoring technology, more specifically, the present invention mainly relates to a rainfall-type geological disaster early warning and forecasting model based on RBFN machine learning and a learning method thereof. Background technique [0002] my country is one of the countries with the most serious geological disasters in the world, among which the frequency of geological disasters induced by rainfall is the highest, the distribution is the widest, and the damage is the most serious. At present, the research methods for rainfall-type geological disasters are mainly concentrated in two categories: one is the statistical analysis method, which collects historical rainfall data and disaster occurrences, and conducts statistical comparative analysis to obtain the relationship between geological disasters and rainfall. The second is the mechanism analysis method, which mainly uses the method of physi...

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
IPC IPC(8): G06Q10/04G06N3/08
CPCG06N3/08G06Q10/04
Inventor 张泰丽徐登财赵晓东伍剑波孙强王赫生
Owner NANJING CENT CHINA GEOLOGICAL SURVEY
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