Jiangxi province small watershed mountain torrent susceptibility mapping method based on lifting algorithm

A susceptibility, small watershed technology, applied in knowledge-based models of computer systems, neural learning methods, computing, etc., to achieve the effect of accurate torrent susceptibility

Pending Publication Date: 2022-05-13
HOHAI UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, scholars at home and abroad have not yet reached a consensus on which integrated machine learning method is more suitable for flash flood susceptibility analysis. Further research is needed on whether the flash flood susceptibility assessment method applicable to foreign regions is applicable to domestic flash flood analysis , therefore, more research is needed for flash flood susceptibility assessment and mapping studies

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
  • Jiangxi province small watershed mountain torrent susceptibility mapping method based on lifting algorithm
  • Jiangxi province small watershed mountain torrent susceptibility mapping method based on lifting algorithm
  • Jiangxi province small watershed mountain torrent susceptibility mapping method based on lifting algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Such as figure 1 As shown, the present invention provides a technical solution, a method for mapping the susceptibility of mountain torrents in small watersheds in Jiangxi Province based on a lifting algorithm, including the following main steps:

[0046] S1. Data preprocessing: sample the data, and randomly divide the sample data into training set, verification set and test set as model input;

[0047] S2. Establishment of the lifting method model: using the above data, three lifting algorithms are used to evaluate the susceptibility of mountain torrent disasters;

[0048] S3. Hyperparameter optimization: use the Bayesian optimization algorithm and verification set data to optimize the hyperparameters of the model to obtain the best parameters for the algorithm to run;

[0049] S4. Run the test set data to verify the accuracy of the algorithm;

[0050] S5. Mapping the susceptibility of mountain torrents in small watersheds: import the results of the susceptibility of...

Embodiment 2

[0074] Taking Jiangxi Province as the research area, this method is used to evaluate the susceptibility of flash floods in each small watershed, and the susceptibility mapping is carried out;

[0075] Such as figure 2 As shown, the specific steps of the technical route of the method are as follows:

[0076] The first step is to preprocess the small watershed dataset:

[0077] Select the average slope, shape coefficient, gradient of the longest confluence path, centroid elevation, terrain humidity index, normalized difference vegetation index, distance from the river, and rainfall with a frequency of 80% within 10 minutes in the data set parameter library. The 10 characteristic factors of flood peak modulus and confluence time are used as the independent variables of integrated regression, and the number of flash floods in history is selected as the regression dependent variable;

[0078] On the basis of data cleaning, standardization and downsampling, 60% is randomly divide...

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 Jiangxi province small watershed mountain torrent susceptibility charting method based on a lifting algorithm, which comprises the following main steps: S1, data preprocessing: performing down-sampling on data, and randomly dividing sample data into a training set, a verification set and a test set as model input; and evaluating the mountain torrent disaster susceptibility by adopting three lifting algorithms. According to the method, the mountain torrent susceptibility model is constructed by adopting AdaBoost, GBDT and XGBoost algorithms. And S3, importing a small watershed mountain torrent susceptibility degree result into GIS software, and quickly and accurately performing mountain torrent susceptibility evaluation and mapping. The integration algorithm based on the lifting method can be effectively combined with the water conservancy big data, and the water conservancy big data is combined with a machine learning algorithm, so that the government and professionals are assisted to carry out accurate space analysis work on the small-watershed mountain torrent problem.

Description

technical field [0001] The invention relates to the technical field of mountain torrent disaster susceptibility assessment and mapping, in particular to a method for mapping the mountain torrent susceptibility of small watersheds in Jiangxi Province based on a lifting algorithm. Background technique [0002] my country's terrain is dominated by mountains and hills, and the climate is a typical East Asian monsoon climate. Summer rainstorms are frequent and concentrated. Such terrain and climate factors can easily lead to serious mountain torrent disasters. Risk assessment and mapping of mountain torrent-prone areas is a way to prevent mountain torrents. Effective means of disasters. In previous studies, the analysis of flash flood susceptibility mainly takes the grid as the basic unit. For example, the Chinese patent CN202110274765.4 discloses "a road flash flood vulnerability evaluation method based on GIS and machine learning" In terms of flash flood susceptibility assessment...

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): G06Q10/06G06Q50/26G06N20/20G06N5/00G06N3/08G06F16/29
CPCG06Q10/06393G06N20/20G06N3/08G06Q50/26G06F16/29G06N5/01Y02A10/40
Inventor 张晓祥管筝印涌强黄诚任立良陈跃红
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