Unlock instant, AI-driven research and patent intelligence for your innovation.

Landslide sensitivity evaluation method based on machine learning

A machine learning and sensitivity technology, applied in instrumentation, climate sustainability, design optimization/simulation, etc., can solve problems such as unpredictability and statistical modeling, and achieve the effect of improving reliability

Pending Publication Date: 2022-08-09
CHONGQING INST OF GEOLOGY & MINERAL RESOURCES +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

One of the limitations of statistical methods is the uncertainty associated with each process
Even though many methods (such as ROC / AUC, etc.) with the goal of assessing the reliability of statistical methods and evaluating the goodness of statistical methods can be implemented, a certain proportion of unpredictability is always strictly tied to statistical modeling

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
  • Landslide sensitivity evaluation method based on machine learning
  • Landslide sensitivity evaluation method based on machine learning
  • Landslide sensitivity evaluation method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following is further described in detail by specific embodiments:

[0027] In the present invention, S1 represents step 1, S101 represents step 01 in S1, S102 represents step 02 in S1, and so on.

[0028] The specific implementation process is as follows:

[0029] Let the study area be the M area.

[0030] S1: Initial data collection of landslides in the study area:

[0031] S101: Landslide Inventory Data Acquisition: Obtain landslide catalogues in the study area through aerial orthophotogrammetry and field surveys. 260 shallow landslides have occurred in Area M, so these landslide data are collected. Since the landslides investigated are polygons, only one highest point is selected, that is, the point with the highest altitude in the landslide area. This is done to be able to run different models that require points as input data.

[0032] S102: Selection of landslide-inducing factors: 13 predictors were selected based on the most representative local morpholog...

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 relates to the field of landslide disaster prediction, and discloses a landslide sensitivity evaluation method based on machine learning. According to the invention, the reliability of the landslide sensitivity map is improved by using different machine learning methods, and the principle is that two or more models may have very similar prediction performance even if they contain different environmental prediction factors and / or they generate distinct spatial predictions. Therefore, it is difficult to know which equivalent candidate model is used, and combination of several models shows that output generated by the models is stronger than that generated by a single model, and set prediction is more stable.

Description

technical field [0001] The invention relates to the field of landslide disaster prediction, in particular to a method for evaluating landslide susceptibility based on machine learning. Background technique [0002] Landslides are one of the major natural disasters with huge and widespread impacts around the world and cause human and socio-economic losses. There is still great uncertainty in the spatiotemporal prediction of landslide risk. Therefore, the identification and mitigation of landslide risk is still a daunting task for local governments. Therefore, landslide susceptibility assessment is very important for the identification of landslide risk. In recent years, due to scientific development, combining numerical deterministic modeling with statistical methods, many methods have been invented aimed at assessing landslide susceptibility mapping (LSM). Deterministic models require information about the physical processes that lead to triggering and therefore involve di...

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 Applications(China)
IPC IPC(8): G06F30/27G06F119/02
CPCG06F30/27G06F2119/02Y02A90/10
Inventor 杨海清陈立川梁丹李卓航徐洪王琦梁振兴王骏
Owner CHONGQING INST OF GEOLOGY & MINERAL RESOURCES