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

Flood warning analysis method and system based on Poisson regression and spatial filtering

A kind of early warning analysis and space technology, applied in the direction of design optimization/simulation, climate change adaptation, etc., can solve the problem of high algorithm complexity, and achieve the effect of improving the accuracy of fitting and prediction

Active Publication Date: 2022-07-19
WUHAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Chun (Chun et al., 2016, see background document 12) pointed out that although the spatial filtering method can effectively solve the problem of spatial autocorrelation and is applicable to different research fields, it also has the disadvantage of high algorithm complexity

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
  • Flood warning analysis method and system based on Poisson regression and spatial filtering
  • Flood warning analysis method and system based on Poisson regression and spatial filtering
  • Flood warning analysis method and system based on Poisson regression and spatial filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] In order to facilitate the understanding, implementation and application of this invention by those skilled in the art, the invention will be further explained below with reference to the accompanying drawings and examples. Not just limited to this invention.

[0066] The embodiment of the present invention adopts a quantitative method based on supervised learning, which can find out the main driving factors of flood warning events in the basin, and predict the expected frequency of the warning events on the whole river, so as to provide decision-making for the location of hydrological stations support.

[0067] In the embodiment, a flood warning analysis method based on Poisson regression and spatial filtering value, the flow is shown in the appendix. figure 1 , perform the following steps:

[0068] Step 1: Count the frequency of flood warning events on the historical observation data (including time, water level, flow, warning water level, station coordinates, etc.) o...

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 proposes a flood early warning analysis method and system based on Poisson regression and spatial filtering value, which includes the frequency statistics of flood early warning events based on historical observation data of hydrological stations in a certain watershed; Hazard factor data, construct a Thiessen polygon for the coordinate points of the hydrological station to obtain the space, and decompose the eigenvalues ​​and eigenvectors; in the case of satisfying the significance test of spatial autocorrelation, carry out forward selection regression, and establish a Poisson based on spatial filtering value. Loose regression model; the selected feature vectors are added to the Poisson regression model together with the disaster-causing and disaster-pregnancy factors as independent variables, and a Poisson regression model of the frequency of flood warning events based on spatial filtering values ​​is constructed to support the realization of the frequency of flood warning events. Fit predictions. The invention can solve the defect of low fitting precision in the prior art, and can be used for the risk prediction of floods and dykes and dams at each site in the whole basin.

Description

technical field [0001] The invention belongs to the category of hydrological statistical analysis and spatial statistical analysis, and uses Poisson regression and spatial filtering method to analyze and realize the flood warning of hydrological stations. Background technique [0002] The dam break caused by flood has caused great loss of people's life and property in history, and is one of the common natural disasters. The risk assessment of flood disasters is mainly based on statistical methods. Qualitative methods mainly use expert opinion or data-driven methods to weight each factor or criterion, such as multi-criteria AHP, fuzzy AHP and supervised machine learning methods. Many scholars have successively used the spatial multi-criteria (fuzzy) analytic hierarchy process to model the flood risk and vulnerability in the Dongting Lake region (Yamei Wang et al., 2011, see Reference 1,; Yun Chen et al., 2015 , see Reference 2). AHP is inherently subjective because it is a...

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): G06F30/20
CPCG06F30/20Y02A10/40
Inventor 陈玉敏方涛李慧芳谭黄元曹吉平罗凤兰
Owner WUHAN 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