Waterlogging simulation optimization and intelligent monitoring method based on computer vision

By reshaping land use data using computer vision technology and algorithms, and combining it with a one-dimensional and two-dimensional surface coupling model, the accuracy and computational resource problems of traditional hydrological and hydrodynamic models in simulating urban flooding have been solved, achieving high-precision flooding simulation and intelligent monitoring.

CN122287250APending Publication Date: 2026-06-26HEBEI UNIV OF ENG +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202610557670.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-24
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Traditional hydrological and hydrodynamic models struggle to depict the interaction between two-dimensional surface runoff and pipe network overflow when simulating urban flooding. High-precision two-dimensional models consume significant computational resources and have complex parameters. Furthermore, the model's input data has limited classification accuracy, leading to significant discrepancies between simulation results and actual water accumulation distribution.

Method used

We used computer vision technology combined with SegNet and U-Net algorithms to segment land use data, reshape the underlying surface, and construct new land use data. We then combined the stormwater runoff management model SWMM and the land surface flux integrated flood forecasting model ITF-FLOOD to construct a one-dimensional and two-dimensional surface coupled model. We used formulas such as the Green-Ampt infiltration intensity equation, the two-dimensional groundwater equation, and the momentum equation to calculate the depth and area of ​​surface water accumulation.

Benefits of technology

It improves the accuracy of urban flooding model simulation, provides a more intelligent and convenient monitoring method, and significantly enhances the accuracy of urban flooding simulation and monitoring.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a waterlogging simulation optimization and intelligent monitoring method based on computer vision, and belongs to the technical field of flood model monitoring, and the method comprises the steps: determining a research region, and building a one-dimensional hydrodynamic model of a water network based on initial modeling data; based on computer vision, land utilization data of a research area is segmented and extracted by using a SagNet algorithm and a U-Net algorithm, an underlying surface is remodeled, new land utilization data is constructed, and new uncertainty parameters are calculated; comparing and analyzing the performance of the one-dimensional hydrodynamic model before and after updating the uncertainty parameters; and a two-dimensional earth surface coupling model combined with the land surface flux integrated flood forecasting model ITF-FLOOD is constructed, and the two-dimensional earth surface coupling model is used for simulating the depth and the area of surface accumulated water in the research area to complete simulation optimization and intelligent monitoring of waterlogging. The waterlogging model simulation precision can be improved, and a more intelligent and convenient monitoring method is provided for waterlogging-prone points.
Need to check novelty before this filing date? Find Prior Art