Flood forecasting method and system based on multi-scale memory and deep learning in data-scarce areas

By constructing a flood forecasting method based on multi-scale memory and deep learning, and combining graph convolutional networks and long short-term memory networks, the problem of not considering spatiotemporal characteristics in flood forecasting is solved, and high-precision flood forecasting is achieved for areas with scarce data.

CN120764765BActive Publication Date: 2026-07-24HUAZHONG UNIV OF SCI & TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202510893633.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-30
Publication Date
2026-07-24
Estimated Expiration
2045-06-30

AI Technical Summary

Technical Problem

Existing flood prediction models mainly handle missing values ​​from a time perspective, failing to fully consider the complex spatiotemporal characteristics of flood runoff data, and their prediction accuracy needs further improvement.

Method used

A method based on multi-scale memory and deep learning is adopted to construct single-point spatiotemporal features by obtaining the temporal and spatial correlation of missing values. The generated values ​​of flood runoff are generated using a multi-scale memory network, and flood forecasting is performed by combining graph convolutional networks and long short-term memory networks.

Benefits of technology

It improves the accuracy of missing value handling and prediction precision, better captures the spatiotemporal relationships between hydrological stations, enhances the performance and reliability of prediction models, and improves the accuracy of flood prediction in areas with scarce data.

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

Abstract

The present application belongs to the technical field of hydrological forecast, and discloses a flood forecasting method and system in a region with insufficient data based on multi-scale memory and deep learning, wherein the method comprises the following steps: collecting observation value data of flood runoff of multiple hydrological stations; for missing values, acquiring time correlation quantity according to time-close observation value information, acquiring space correlation quantity according to space-close observation value information, so as to acquire single-point space-time characteristics of the missing values; acquiring local space-time characteristics including characteristics of all hydrological stations; inputting the local space-time characteristics into a multi-scale memory network storing multiple scale observation value data to output generated value data to realize runoff embedding; and performing flood forecasting based on runoff data after runoff embedding. The present application comprehensively considers space-time relationship of hydrological stations to extract characteristics of missing values, and fuses multi-scale historical characteristics and local space-time characteristics through a multi-scale memory network structure, so that current characteristic embedding can be enhanced, thereby improving prediction accuracy.
Need to check novelty before this filing date? Find Prior Art