Hydrological trend prediction method based on big data analysis

By constructing a graph structure based on geographical distance and water system connectivity, combining message delivery mechanism and neural network, dynamically adjusting model parameters, the problems of spatial correlation and dynamic evolution in hydrological trend prediction in the basin are solved, and high-precision and adaptive hydrological prediction are achieved.

CN120450142AActive Publication Date: 2025-08-08广东省水文局江门水文分局
5 Cites 8 Cited by

Patent Information

Application Number
CN202510584580.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-07
Publication Date
2025-08-08
Estimated Expiration
2045-05-07

AI Technical Summary

Technical Problem

The existing hydrological trend prediction methods fail to effectively capture the spatial correlation between sites in the basin and its dynamic evolution process, resulting in insufficient model accuracy and adaptability, especially in the dynamic adjustment of connectivity caused by changes in rainfall intensity.

Method used

The initial graph structure is constructed, the edge weight is calculated based on geographical distance and water system connectivity, and the node features iteratively aggregated through the message delivery mechanism, combined with the graph neural network, dynamic Bayesian network and space-time collaborative Krigin interpolation algorithm, dynamically adjust the graph structure and parameters to form an adaptive prediction process.

Benefits of technology

Accurately capture the dynamic correlation of hydrological elements in the basin, improve the dynamic modeling ability of emergencies, and realize the fusion of the spatial topology and time series of hourly hydrological variables, ensuring high accuracy and stability in different environments.

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

Abstract

The invention provides a hydrological trend prediction method based on big data analysis, and the method comprises the steps: building an initial graph structure which takes a monitoring station as a node and geographic distance and water system connectivity as an edge weight, carrying out the iterative aggregation of node features through a message passing mechanism, and capturing the space interaction of hydrological variables between stations; dynamically adjusting a water system connectivity parameter and an edge weight based on rainfall change, and generating an adaptive graph structure; in combination with the graph neural network, the dynamic Bayesian network and the space-time collaborative Kriging interpolation algorithm, hour-level hydrological dynamic transmission features are extracted, and a space-time coupling prediction model is formed; model parameter optimization and message passing mechanism adjustment are triggered through a prediction deviation threshold value, and a self-adaptive prediction process of'dynamic modeling-feature fusion-closed loop optimization 'is realized. According to the method, hydrological element space-time correlation can be accurately described, the analysis precision of a complex hydrological process is improved, and the adaptability to sudden hydrological events and basin environment changes is enhanced.
Need to check novelty before this filing date? Find Prior Art