Mountain torrent disaster susceptibility evaluation method based on GIS and ensemble learning

An integrated learning and evaluation method technology, applied in the field of mountain torrent disaster susceptibility evaluation based on GIS and integrated learning, can solve the problems of poor learning effect of a single machine, and achieve the effect of reliable principle, accurate calculation, and easy-to-learn operation process

Pending Publication Date: 2022-05-13
HOHAI UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a method for evaluating the susceptibility of mountain torrent disasters based on GIS and integrated learning, which can effectively solve the problem that single machine learning is less effective in dealing with nonlinear problems in the above-mentioned background technology

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
  • Mountain torrent disaster susceptibility evaluation method based on GIS and ensemble learning
  • Mountain torrent disaster susceptibility evaluation method based on GIS and ensemble learning
  • Mountain torrent disaster susceptibility evaluation method based on GIS and ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] Example: such as figure 1 As shown, the present invention provides a kind of technical scheme, a kind of flash flood disaster susceptibility evaluation method based on GIS and ensemble learning, uses multivariate self-adaptive regression spline (MARS) and random forest (RF) algorithm as ensemble learning basic model, Using artificial neural network (ANN) algorithm integration, 3860 small watershed vector units are used as the research object, and 13 mountain torrent characteristic factors are selected as regression independent variables;

[0046] The evaluation method specifically includes the following steps:

[0047] The first step is data preprocessing;

[0048]The second step is to build the model;

[0049] The third step is the influence of characteristic factors;

[0050] The fourth step is to verify the performance of the algorithm;

[0051] The fifth step is the mapping of flash flood susceptibility.

[0052] Based on the above technical solutions, in the f...

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 mountain torrent disaster susceptibility evaluation method based on a GIS and ensemble learning. A multivariate adaptive regression spline (MARS) and a random forest (RF) algorithm are used as an ensemble learning basic model, an artificial neural network (ANN) algorithm is used for integration, a plurality of small watershed vector units are used as research objects, and a plurality of mountain torrent characteristic factors are selected as regression independent variables. According to the method, the vector small watershed is used as a basic research unit, the easy-to-occur degree of the small watershed area can be analyzed more accurately, and therefore the small watershed where mountain torrents occur easily can be positioned accurately. Meanwhile, a mountain torrent disaster investigation evaluation result is combined with machine learning and an intelligent algorithm, so that mountain torrent disaster susceptibility evaluation and mapping are carried out, and the provided evaluation method is accurate in calculation, reliable in principle, easy and convenient to learn in the operation process and capable of being universally suitable for the requirement of provincial scale mountain torrent disaster susceptibility evaluation; and auxiliary decisions are provided for mountain torrent disaster prevention and control.

Description

technical field [0001] The invention relates to the technical field of mountain torrent disaster susceptibility evaluation and mapping, in particular to a method for evaluating mountain torrent disaster susceptibility based on GIS and integrated learning. Background technique [0002] Risk assessment and mapping of flash flood-prone areas is an effective means of preventing flash flood disasters. At present, there are many patents for flash flood risk susceptibility assessment and mapping. In previous studies, the analysis of flash flood susceptibility is mainly based on The grid is the evaluation unit, such as a method for evaluating road torrent vulnerability based on GIS and machine learning disclosed in patent 202110274765.4; [0003] In the analysis method of mountain torrent disaster susceptibility, traditional spatial analysis methods have been widely used. Traditional evaluation methods such as AHP and catastrophe theory evaluation method, such as a method of mountai...

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): G06Q10/06G06Q50/26G06N20/20G06N3/08G06F16/29
CPCG06Q10/0639G06N20/20G06F16/29G06Q50/26G06N3/08Y02A10/40
Inventor 张晓祥黄诚印涌强管筝任立良陈跃红
Owner HOHAI UNIV
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