A classification-based stochastic flood forecasting method based on machine learning and cloud model

Through the classified flood random forecasting method based on machine learning and cloud models, the problem of model uncertainty and moment correlation in flood forecasting is solved, and flood forecasting with higher accuracy and reliability is achieved.

CN115759445BActive Publication Date: 2025-09-05ZHEJIANG UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202211486193.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-24
Publication Date
2025-09-05
Estimated Expiration
2042-11-24

AI Technical Summary

Technical Problem

The existing flood forecasting technology fails to effectively consider the correlation between model uncertainty and forecast moment, resulting in unavoidable forecast errors, and multi-model fusion methods fail to make full use of similarities between models.

Method used

A random prediction method of classified flood based on machine learning and cloud models is adopted, and a random prediction of floods is classified through self-organized mapping neural networks, influencing factors are screened, multiple machine learning models are established, cloud models are used for weighted fusion, and the correlation of forecast errors is modeled through the Copula method, and random simulation is performed in combination with Gibbs sampling to achieve random prediction of floods.

Benefits of technology

It improves the accuracy and reliability of flood forecasting, can effectively reduce the risks of a single model, make up for model uncertainty, and improves the accuracy of random forecasting.

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

Abstract

This invention discloses a random flood forecasting method based on machine learning and cloud models. The steps are as follows: using typical historical floods as basic data for model calibration and testing, selecting classification indicators that meet the conditions, and classifying historical floods based on a self-organizing map neural network (SOM); using the maximum information coefficient method (MIC) to screen the impact factors of classified floods, and establishing a random flood forecasting model based on different machine learning methods; for different types of floods, solving the fusion weights of different forecasting models based on the cloud model, and weighting the simulation results of each model to obtain the model integrated forecast result; analyzing and calculating the relative forecast error, and establishing the joint distribution function of the relative forecast errors at adjacent moments based on the Copula method; finally, obtaining real-time online flood information to achieve random flood forecasting. This invention can improve the accuracy of flood forecasting and provide a new approach to hydrological prediction and forecasting.
Need to check novelty before this filing date? Find Prior Art