Space-time intelligent early warning method and system for soil landslide disasters

A disaster and alarm technology, applied in the fields of instruments, character and pattern recognition, data processing applications, etc., can solve the problems of poor real-time performance, high false alarm rate, and long calculation time.

Inactive Publication Date: 2020-11-20
CHENGDU UNIV OF INFORMATION TECH +1
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The statistical pre-alarm mode is to analyze landslide events and corresponding rainfall data to obtain the rainfall threshold conditions that trigger landslides. This statistical mode relies too much on observed precipitation and rarely considers the influence of underlying surface factors, resulting in a high false alarm rate; Although the disaster mechanism early-warning model solves the defect that the statistical early-warning model is too dependent on precipitation, due to the complexity of the landslide disaster mechanism and the diversification of triggering factors, this kind of early-warning model needs to set more assumptions in advance. It can roughly simulate the development process of landslides, but cannot accurately and comprehensively describe the entire development process of landslide hazards
In addition, because the disaster mechanism early warning model needs to simulate the development process of landslides, the calculation time is too long, the real-time performance is poor, and it is difficult to put it into business use

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
  • Space-time intelligent early warning method and system for soil landslide disasters
  • Space-time intelligent early warning method and system for soil landslide disasters
  • Space-time intelligent early warning method and system for soil landslide disasters

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] refer to figure 1 , is a structural schematic diagram of an intelligent learning module for landslide disaster early warning in the present invention, specifically, an intelligent learning module for landslide disaster early warning, including a plurality of base modules and meta modules; wherein,

[0056] The basic module is used to receive the data of the training set for calculation and training to obtain the prediction results; the prediction results of each basic module construct a new first data set, which is used as the input of the meta-module, and the expected output of the first data set is consistent with each basic module.

[0057] In this embodiment, the selection of appropriate basic modules and meta-modules has a greater impact on the final results. Generally, different types of weak learning machines are selected, such as naive Bayesian, K-nearest neighbors, decision trees, and logistic regression, etc. Module, choose the random forest classifier as the ...

Embodiment 2

[0060] Based on the module of embodiment 1, a kind of space-time intelligent early-warning system of soil landslide disaster is provided in the present embodiment, and concrete structural diagram can refer to figure 2 , a spatio-temporal intelligent warning system for soil landslide disasters, including:

[0061] Data acquisition module 3, for obtaining landslide hazard point data and non-landslide hazard point data;

[0062] In the present embodiment, the data of landslide disaster point includes: landslide disaster occurrence time, place; Non-landslide disaster point data includes time, place; Wherein,

[0063] The location in the non-landslide disaster point is the place where there is no landslide at the 1-2km around the landslide disaster point, and the time is the time adjacent to the landslide disaster point, or the place is a slope body site that is affected by heavy rainfall but does not have a landslide disaster, The time is the time when the corresponding location...

Embodiment 3

[0078] Based on the system of embodiment 2, a kind of space-time intelligent early-warning method of soil landslide disaster is disclosed in this embodiment, image 3 It is a schematic flow chart of the method; specifically, a space-time intelligent early warning method for soil landslide disasters, comprising the following steps:

[0079] S100: Obtain landslide hazard point data and non-landslide hazard point data; then perform step S200;

[0080] In this embodiment, the data of the landslide disaster point includes: landslide disaster occurrence time, place (latitude and longitude coordinates); The spatial distribution characteristics, cause mechanism and development environment of landslide disasters, the time of occurrence of landslide disasters collected so far is only accurate to the day. Since some landslide disasters occurred long ago, the exact latitude and longitude coordinates where the landslide disaster occurred were not recorded, but only the village group where...

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 provides a space-time intelligent early warning method and system for soil landslide disasters. The method comprises the steps: acquiring landslide disaster point data and non-landslidedisaster point data; acquiring a landslide disaster early warning factor for intelligent learning according to the cause mechanism and the induction factor of the landslide disaster; acquiring original data corresponding to the early warning factor according to the landslide disaster point data and the non-landslide disaster point data; performing spatial analysis on the original data to extract values of landslide early warning factors for intelligent learning, and performing dimensionless processing on the obtained values of the early warning factors to construct a landslide disaster early warning sample data set; adopting an integrated machine learning stack generalization method to build an intelligent learning module used for landslide disaster early warning, wherein a landslide disaster early warning sample data set is input into the intelligent learning module to be trained and optimized, and early warning of landslide disasters is achieved. The method is high in accuracy, low in false alarm rate, short in calculation time and good in real-time performance during landslide prediction.

Description

technical field [0001] The invention belongs to the technical field of landslide prevention and control engineering, and in particular relates to a time-space intelligent early warning method and system for soil landslide disasters. Background technique [0002] At present, the early warning methods of regional landslide disasters are mainly divided into two categories, including: the statistical early warning model and the disaster mechanism early warning model. The statistical pre-alarm mode is to analyze landslide events and corresponding rainfall data to obtain the rainfall threshold conditions that trigger landslides. This statistical mode relies too much on observed precipitation and rarely considers the influence of underlying surface factors, resulting in a high false alarm rate; Although the disaster mechanism early-warning model solves the defect that the statistical early-warning model is too dependent on precipitation, due to the complexity of the landslide disas...

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): G06K9/62G06Q50/26
CPCG06Q50/26G06F18/24155G06F18/214
Inventor 刘敦龙吴倩唐聃何磊高燕罗涵
Owner CHENGDU UNIV OF INFORMATION TECH
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