Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Debris flow early warning method and system based on mechanism and machine learning coupling

A machine learning and early warning system technology, applied to instruments, alarms, climate sustainability, etc., can solve problems such as not taking into account the mechanism and process of debris flow, so as to improve forecast accuracy, comprehensive and accurate forecast results, and reduce false alarm rate Effect

Active Publication Date: 2021-01-15
INST OF MOUNTAIN HAZARDS & ENVIRONMENT CHINESE ACADEMY OF SCI
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current machine learning models that use grid or small watershed units as forecast units do not take into account the mechanism process of debris flow, and still belong to the category of mathematical statistics

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
  • Debris flow early warning method and system based on mechanism and machine learning coupling
  • Debris flow early warning method and system based on mechanism and machine learning coupling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Such as figure 2 As shown, a debris flow early warning system based on the coupling of mechanism and machine learning includes a eigenvector set unit, a data input unit, and a model training unit; the eigenvalue parameters of the eigenvector set unit include historical precipitation values, forecast precipitation values, lower Data value of backing surface, risk level value of debris flow based on small watershed unit P i , i is the total number of small watershed units in the region;

[0032] The data input unit is used to input the feature vector set unit into the machine learning model;

[0033]The model training unit is used to train the machine learning model by calling the function interface in the machine learning library sklearn according to the data characteristics of the feature vector set, and perform machine learning model testing and parameter tuning.

[0034] In implementation, the machine learning model may be one of support vector machine SVM, linear ...

Embodiment 2

[0037] The support vector machine SVM and the built-in kernel function of the kernel function are used as the linear kernel function linear for further explanation.

[0038] A debris flow early warning method based on the coupling of mechanism and machine learning, including the following steps:

[0039] (1) Construct a database of geological hazards and rainfall.

[0040] ① Debris flow disaster data: Collect the debris flow disaster data in the study area over the years. The disaster data includes the location (latitude and longitude) of the debris flow and the time when the debris flow occurred.

[0041] ② Underlying surface data: The small watershed units in the study area were extracted using the method of the paper "A Regional-Scale Method of Forecasting DebrisFlow Events Based on Water-Soil Coupling Mechanism". Number each small watershed unit (the maximum number is denoted as Nmax). The polygon file is then converted to a raster file with the same cell size as the dig...

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 debris flow early warning system based on mechanism and machine learning coupling. The debris flow early warning system comprises a feature vector set unit, a data input unitand a model training unit. The data input unit is used for inputting the feature vector set unit into a machine learning model; and the model training unit is used for training a machine learning model by calling a function interface in a machine learning library sklearn and testing the machine learning model. The invention further discloses a debris flow early warning method. The debris flow early warning method comprises the following steps: S1, constructing a feature vector set of the unstable small watershed unit and the stable small watershed unit; s2, based on the data characteristics of the feature vector set, selecting a machine learning model, and based on a machine learning library sklearn with a built-in appropriate kernel function, establishing a debris flow disaster prediction model; s3, and carrying out forecasting. The prediction accuracy can be effectively improved, and the false alarm rate of the model is reduced.

Description

technical field [0001] The invention relates to early warning of rainfall-induced debris flow, belongs to the technical field of debris flow disaster prevention, and in particular relates to a debris flow early warning method and system based on mechanism and machine learning coupling. Background technique [0002] Missed alarm rate and false alarm rate are the main parameters to evaluate the service level of geological disaster early warning system. At present, the missed alarm rate of the system including the statistical forecasting model is relatively low, but the problem of high false alarm rate cannot be avoided. The application results of the Sichuan Provincial Meteorological Bureau show that the false alarm rate of the new system has been reduced from 80%-90% of the statistical forecast to about 30%, which is the same as the false alarm rate of the geological disaster early warning system operated by the Chongqing Land and Resources Bureau in 2017. Levels (around 35%)...

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): G08B21/10
CPCG08B21/10Y02A90/10
Inventor 张少杰杨红娟刘敦龙王凯
Owner INST OF MOUNTAIN HAZARDS & ENVIRONMENT CHINESE ACADEMY OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com