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

A local area landslide prediction device and method

A local area and prediction method technology, applied in the direction of prediction, neural learning methods, data processing applications, etc., can solve the problems that affect the prediction accuracy, the prediction accuracy is not high, and the stable model cannot be obtained, so as to achieve the goal of improving the prediction accuracy Effect

Active Publication Date: 2021-03-23
JIANGSU UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are many landslide prediction methods, some of which use a separate monitoring and prediction method for displacement factors, but because landslides are also affected by many other factors, it affects the prediction accuracy; some use GM models, which are suitable for short-term prediction, but in the establishment In the long-term forecasting model, due to the long data column, the unstable factors increase and the prediction accuracy of the model decreases; some traditional Bayesian models cannot obtain a stable model, and need to be remodeled after each data change; Some use Logistic regression, which requires discretization and approximation of independent variables, causing errors and affecting prediction accuracy
The current landslide prediction method can realize the prediction function, but the prediction accuracy is generally not high

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
  • A local area landslide prediction device and method
  • A local area landslide prediction device and method
  • A local area landslide prediction device and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] Example 1: Areas prone to landslides in hilly areas

[0071] The detection node layout interface diagram of the whole area is composed of Figure 4 shown.

[0072] The training process is as follows:

[0073] Step S1: Local region number Re m , 1≤m≤M, M=12 is the total number of local areas, and the number of monitoring points is Ds n , 1≤n≤N, 1≤m≤N, N=50 is the total number of monitoring points in the local area, and the landslide area data set is The total number of layers of the neural network is Layer=15;

[0074] Step S2: Initialize the current layer of the neural network as layer=Layer, m=1;

[0075] Step S3: k=m, local area Re m The matrix graph training set of S m The sensor data set representing the monitoring point is mapped to a k×k matrix image training set, and the local area Re m During the training process, each time node of the monitoring point sensor data set is t π ,1≤t π ≤T, T is the total training time of the local area. Local area land...

Embodiment 2

[0097] Embodiment 2: Areas prone to landslides in residential quarters

[0098] The detection node layout interface diagram of the whole area is composed of Image 6 shown.

[0099] The training process is as follows:

[0100] Step S1: Local region number Re m , 1≤m≤M, M=10 is the total number of local areas, and the number of monitoring points is Ds n , 1≤n≤N, 1≤m≤N, N=40 is the total number of monitoring points in the local area, and the landslide area data set is The total number of layers of the neural network is Layer=13;

[0101] Step S2: Initialize the current layer of the neural network as layer=Layer, m=1;

[0102] Step S3: k=m, local area Re m The matrix graph training set of S m The sensor data set representing the monitoring point is mapped to a k×k matrix image training set, and the local area Re m During the training process, each time node of the monitoring point sensor data set is t π ,1≤t π≤T, T is the total training time of the local area. Local...

Embodiment 3

[0124] Example 3: Areas prone to landslides along the river

[0125] The detection node layout interface diagram of the whole area is composed of Figure 8 shown.

[0126] The training process is as follows:

[0127] Step S1: Local region number Re m , 1≤m≤M, M=18 is the total number of local areas, and the number of monitoring points is Ds n , 1≤n≤N, 1≤m≤N, N=45 is the total number of monitoring points in the local area, and the landslide area data set is The total number of layers of the neural network is Layer=20;

[0128] Step S2: Initialize the current layer of the neural network as layer=Layer, m=1;

[0129] Step S3: k=m, local area Re m The matrix graph training set of S m The sensor data set representing the monitoring point is mapped to a k×k matrix image training set, and the local area Re m During the training process, each time node of the monitoring point sensor data set is t π ,1≤t π ≤T, T is the total training time of the local area. Local area lan...

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 local region landslide prediction device and a local region landslide prediction method. The existing machine learning related technologies are adopted, including a convolution neural network technology, a supervised policy model, a stochastic gradient descent method, a stochastic gradient ascent method, and a migration model. The steps of a training method and an evaluation method are designed. Input historical landslide data is trained, and a landslide model is built and optimized. The current landslide situation is evaluated by use of the slide model, and the landslide trend and probability of a local region are displayed. The function of local region landslide prediction is achieved. The prediction accuracy is improved. The device and the method can be applied to local region landslide prediction.

Description

technical field [0001] The invention belongs to the field of geological disaster prediction, and in particular relates to a landslide prediction technology. Background technique [0002] Landslide refers to the phenomenon that the soil and rock mass on the slope slides down the slope in whole or in part along a certain weak surface or belt under the action of gravity due to various factors. Landslide events generally cause serious economic losses and even loss of life. Prediction of landslides is a feasible method to reduce landslide hazards. There are many landslide prediction methods, some of which use a separate monitoring and prediction method for displacement factors, but because landslides are also affected by many other factors, it affects the prediction accuracy; some use GM models, which are suitable for short-term prediction, but in the establishment In the long-term forecasting model, due to the long data column, the instability factors increase and the predicti...

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 Patents(China)
IPC IPC(8): G06Q10/04G06N3/08
CPCG06N3/08G06Q10/04
Inventor 陈潇君朱娜蔡文红江晓明
Owner JIANGSU UNIV
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