A Flood Sensitivity Risk Assessment Method Based on Ensemble Learning

Abstract

The invention discloses a flood sensitivity risk assessment method based on integrated learning. Remote sensing data extraction to study historical submerged and non-submerged points in the watershed; use Laplacian score to select the optimal feature subset; divide sample points into training set and test set and train the ensemble learning model; use the trained model Flood risk sensitivity calculation is performed for the entire watershed to generate a flood sensitivity risk level distribution map of the watershed. The invention uses each characteristic data of the research area as input, adopts a novel integrated learning model, improves the accuracy of flood risk assessment in the basin, and finally generates a flood risk map of the basin, which can intuitively display the flood risk status of the research area.

Description

technical field [0001] The invention belongs to the technical field of flood disaster risk assessment, in particular to an integrated learning-based flood sensitivity risk assessment method. Background technique [0002] Flood disaster is a kind of destructive, sudden and high frequency natural disaster. China is one of the countries with the most frequent flood disasters, which cause a large number of economic losses and casualties every year, so the research in the field of flood risk sensitivity assessment is of great significance. Flood risk sensitivity assessment is a comprehensive evaluation of the natural and social attributes of regional flood disasters, aiming to more accurately grasp the spatial distribution and occurrence rules of flood risks. As flood risk sensitivity assessment is a very complex process involving multiple evaluation indicators, it has always been one of the difficulties and hot spots in disaster research at home and abroad. [0003] With the d...

AI Technical Summary

Problems solved by technology

However, this method needs to collect a large amount of natural and social data as input. Once the amount of data is low or the quality of the data is not high, it will cause relatively large deviations in the results.

On the other hand, this method requires high professional knowledge of operators, and when the number of flood impact factors is large, it will cause confusion in the judgment of operators, which will affect the evaluation results

[0004] The random forest-based flood risk assessment method proposed by Lai Chengguang et al. on page 58 of the first issue of Volume 46 of "Journal of Water Resources" in January 2015 simplifies the risk assessment process, but has a relatively long running time and low accuracy. not high problem

[0005] To sum up, the existing flood susceptibility risk assessment methods have the following defects: (1) A large amount of natural and social data are required, and the workload of data collection is heavy

(2) Higher professional knowledge requirements for operators

(3) The operation takes a long time and the accuracy is relatively low

Images