Runoff probability forecasting method

Abstract

The invention discloses a runoff probability forecasting method, wherein, the method mainly comprises the following steps: adopting a method based on K. Medoids clustering method is used to cluster the training set, and the initialization parameters of HMM are obtained. Using Baum-Welch algorithm to study HMM, the state transition probability matrix of HMM and the probability distribution of observation model are obtained. According to Bayesian Information Criterion (BIC), the model is selected and the number of HMM states suitable for the training set is selected. Finally, the conditional probability distribution function is obtained by Gaussian mixture regression GMR reasoning according to the given forecasting factors as the runoff probability forecast. The probability forecasting method of the invention introduces the concept of runoff hidden state, and can obtain the hidden state transition probability matrix by using hydrology, topography, meteorology and other factors, and obtain effective and reliable future runoff probability forecasting distribution, thereby providing scientific basis for reservoir optimal operation and decision-making.

Description

technical field [0001] The invention relates to the field of hydrology and water resources, and more specifically, to a runoff probability forecasting method. Background technique [0002] Runoff forecasting can play an important role in all aspects of reservoir operation and management, such as flood control, water supply, and power generation. High-precision and reliable forecasts can provide a scientific basis for optimal dispatching of cascade reservoirs in the basin, and are of great significance to the rational use of water resources in the basin. However, the formation process of rainfall runoff is affected by many natural factors such as hydrology, topography, and meteorology, and presents highly nonlinear, random, and uncertain characteristics, which brings difficulties to runoff prediction. It is difficult to use traditional methods to carry out runoff prediction . Therefore, how to construct a prediction model that considers many hidden factors affecting the run...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the defects of the prior art, the purpose of the present invention is to solve the problem that the formation process of the existing rainfall runoff is affected by many natural factors such as hydrology, topography, and meteorology, and presents highly nonlinear, random and uncertain characteristics, and provides a comprehensive solution for runoff prediction. It has brought difficulties, it is difficult to use traditional methods to carry out runoff prediction, and the technical problem of how to predict the future runoff sequence through the trained hidden Markov model

Images