Hybrid model for daily runoff interval predictions based on Bayesian inference

ABSTRACT

The highly non-linear and nonstationary nature of runoff events in changing environments makes accurate and reliable runoff forecasting difficult. We propose a hybrid model by integrating an autoregressive (AR) model, Bayesian inference, a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm, Bayesian optimization, and support vector regression. Two Bayesian inference methods (the No-U-Turn Sampler (NUTS) and variational inference) were used to calculate the parameters of the AR model to obtain a Bayesian AR (BAR) model. Credible intervals were used to analyse the uncertainty of the parameters and model prediction results. The above model is applied to the daily runoff predictions of hydrological stations in the Yellow River basin of China. The results show that (1) the hybrid model can improve the prediction accuracy and (2) the NUTS algorithm-based model provides a narrower reliable interval and performs better in uncertainty analyses.

KEYWORDS:

• Bayesian inference
• autoregressive model
• support vector regression
• Bayesian optimization algorithm
• daily runoff prediction
• Yellow River basin

Editor A. Castellarin Associate Editor E. Volpi

Editor A. Castellarin Associate Editor E. Volpi

Acknowledgements

The authors express their cordial gratitude to the editors and anonymous reviewers for their illuminating comments which greatly helped improve the quality of this article.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [51479171, 52079110].