Hydraulic runoff simulation method based on digital twinning

By constructing three-dimensional geometric and hydrodynamic models, and combining deep learning technology to optimize grid partitioning and time step, the accuracy and timeliness issues of flood season runoff prediction in complex river network areas have been solved, enabling precise simulation and flood control scheduling support for high-risk areas.

CN121435833BActive Publication Date: 2026-06-09JINGGANGSHAN UNIVERSITY
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
JINGGANGSHAN UNIVERSITY
Filing Date
2025-11-03
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Traditional hydrological models are insufficient in terms of accuracy and timeliness in predicting flood season runoff in complex river network areas. In particular, the simulation is not precise enough in areas with high runoff volume and high risk, which leads to increased computational costs and reduced simulation accuracy in key areas.

Method used

A digital twin-based water runoff simulation method is adopted. By acquiring digital elevation data and remote sensing images of the target watershed, a three-dimensional geometric model is constructed, high-risk areas are identified, and grid subdivision strategy is used to refine the grid cells. Real-time simulation and deviation analysis are carried out by combining hydrodynamic model and deep learning model, and the grid subdivision and time step are optimized to improve the simulation accuracy.

Benefits of technology

It enables accurate simulation of high-catchment and high-risk areas, improves the scientificity and reliability of runoff forecasting during the flood season, and provides efficient flood control scheduling support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121435833B_ABST
    Figure CN121435833B_ABST
Patent Text Reader

Abstract

The application discloses a water conservancy runoff simulation method based on digital twinning, relates to the technical field of water conservancy runoff simulation, and comprises the following steps: constructing a three-dimensional geometric model of a basin according to digital elevation data and remote sensing images of a target basin, introducing a hydrodynamic model to construct a digital twinning model, simulating flood peak propagation, flow velocity distribution and water level change, introducing a deep learning model to compare and analyze measured hydrological data and historical flood cases, identifying the weight of deviation correction risk indexes of simulation results and measured results, and adjusting a local grid subdivision strategy and boundary conditions. Through the refinement of the grid and the correction of the boundary conditions, the digital twinning model can more accurately reflect the local flow velocity and water level fluctuation when coping with short-time heavy rain, the real-time simulation can not only output physical quantities in the water flow propagation process, but also dynamically identify dangerous areas based on updated risk indexes, and time advantages are provided for flood control plans.
Need to check novelty before this filing date? Find Prior Art