Runoff prediction method and system based on interpretable Bayesian gating circulation unit
By introducing an interpretable Bayesian Gated Cycle Unit (EB-GRU) model in hydrological runoff prediction, the shortcomings of existing models in terms of interpretability and uncertainty quantification are solved, and higher prediction accuracy and interpretability are achieved.
Patent Information
- Application Number
- CN202411680544.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-22
- Publication Date
- 2025-03-11
AI Technical Summary
Existing deep learning models lack interpretability and uncertainty quantification capabilities in hydrological runoff prediction, making it difficult to obtain reliable prediction results, especially in complex and variable hydrological systems.
A runoff prediction method based on an interpretable Bayesian gated cycle unit (EB-GRU) model is proposed. Through Bayesian inference and SHAP methods, the GRU model is optimized to improve the interpretability and uncertainty quantization ability of the model.
The runoff prediction accuracy is improved, the uncertainty in the prediction process is effectively quantified, and the explanatory analysis of the contribution of hydrological meteorological factors is provided, which enhances the interpretability and practicality of the model.