A variation reasoning Bayesian neural network-based flood ensemble forecasting method

Abstract

The invention discloses a variation reasoning Bayesian neural network-based flood ensemble forecasting method. The method comprises the following steps of: setting dimensions of each layer of a Bayesian neural network; Selecting the prior probability distribution of the weight parameters of the Bayesian neural network, and parameterizing the weight parameters of the Bayesian neural network throughthe variational parameters to approximate the posterior probability distribution of the weight parameters of the Bayesian neural network; Calculating the relative entropy of the prior probability distribution and the variation posterior probability distribution, and calculating an expected log-likelihood function according to the training data set; Constructing an objective function according tothe relative entropy and the expected log-likelihood function; maximizing a target function, and training variational reasoning parameters; And carrying out ensemble forecasting on unknown flood by using the trained variational reasoning Bayesian neural network. According to the method, the variational reasoning is combined with the BNN model, and the posterior probability of the weight parametersof the Bayesian network model is approximated through variational distribution, so that the calculation process is simplified, the uncertainty of flood forecasting is quantitatively described, and the accuracy is improved.

Description

technical field [0001] The invention belongs to the field of hydrology and water resources, and more specifically relates to a flood ensemble forecasting method based on variational reasoning Bayesian neural network. Background technique [0002] Accurate and reliable flood forecasting can provide a scientific basis for decision-making on flood control of cascade reservoirs in the basin, and is of great significance to the safety of flood control in the basin and the rational use of flood resources. Moving average autoregressive, support vector machine regression, and deep learning methods have demonstrated their excellent performance in hydrological forecasting. Uncertainty in forecast is also very important in flood control dispatching. However, this type of deterministic forecasting method can only forecast one value and cannot quantify the uncertainty in forecasting. Therefore, it is an urgent theoretical and practical engineering problem to construct an ensemble foreca...

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 technical problems of high computational cost of flood ensemble forecasting and complex optimization caused by many hyperparameters in the prior art

Images