A method and device for reconstructing surface rainfall distribution based on a spatio-temporal graph neural network

By using a spatiotemporal graph neural network reconstruction method, combined with a microwave rain attenuation physical model and uncertainty perception, the problem of reconstructing the surface rainfall distribution of microwave link observations was solved, and high-precision and reliable surface rainfall distribution map generation was achieved.

CN121705669BActive Publication Date: 2026-05-29WUHAN UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202610213018.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-02-13
Publication Date
2026-05-29
Estimated Expiration
2046-02-13

AI Technical Summary

Technical Problem

Existing technologies cannot effectively reconstruct the areal rainfall distribution observed by microwave links, ignoring the spatial topological associations and spatiotemporal dynamic evolution patterns between link paths, resulting in biased positioning of rainfall centers and loss of texture details, and the lack of physical constraints leads to ill-conditioned solutions.

Method used

A spatiotemporal graph structure model is constructed using a spatiotemporal graph neural network approach. Combined with a microwave rain attenuation physical model and uncertainty perception, feature extraction and fusion are performed through a hierarchical spatiotemporal graph neural network to generate a high-resolution rainfall intensity distribution map and establish a real-time inference system.

Benefits of technology

It achieves high-precision reconstruction from linear average to surface distribution, adaptively learns complex spatiotemporal patterns of precipitation fields, improves inversion accuracy and reliability, and provides high-resolution precipitation field distribution maps for credibility assessment.

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

Abstract

The application discloses a kind of face rainfall distribution reconstruction method and device based on space-time graph neural network, wherein the method first constructs space-time graph structure model, the complex spatial correlation between links is established by the adjacency matrix construction method of multi-factor fusion, and the graph structure data object containing space-time dimension is constructed;Further, hierarchical space-time graph neural network is used for feature extraction and fusion, and the space-time depth feature representation of the fused rainfall field is obtained;In the model optimization process, the microwave rain attenuation physical model is introduced as a constraint condition simultaneously, and the physical consistency loss function is used to ensure that the inversion result conforms to the electromagnetic wave propagation law;Based on the grid rainfall intensity and its uncertainty evaluation output by the network, high-resolution surface rainfall distribution products are generated through spatial interpolation and quality control;Finally, a real-time inference system and feedback mechanism are established to dynamically update and output the rainfall field, providing an intelligent technical solution from "line measurement" to "surface reconstruction" for meteorological and hydrological monitoring.
Need to check novelty before this filing date? Find Prior Art