Explicitly integrating parameter, input, and structure uncertainties into Bayesian Neural Networks for probabilistic hydrologic forecasting
Estimating uncertainty of hydrologic forecasting is valuable to water resources and other relevant decision making processes. Recently, Bayesian Neural Networks (BNNs) have been proved powerful tools for quantifying uncertainty of streamflow forecasting. In this study, we propose a Markov Chain Monte Carlo (MCMC) framework to incorporate the uncertainties associated with input, model structure, and parameter into BNNs. This framework allows the structure of the neural networks to change by removing or adding connections between neurons and enables scaling of input data by using rainfall multipliers. The results show that the new BNNs outperform the BNNs that only consider uncertainties associated with parameter and model structure. Critical evaluation of posterior distribution of neural network weights, number of effective connections, rainfall multipliers, and hyper-parameters show that the assumptions held in our BNNs are not well supported. Further understanding of characteristics of different uncertainty sources and including output error into the MCMC framework are expected to enhance the application of neural networks for uncertainty analysis of hydrologic forecasting.
- Research Organization:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 1033073
- Report Number(s):
- PNNL-SA-79220; KP1702020
- Journal Information:
- Journal of Hydrology, Journal Name: Journal of Hydrology Journal Issue: 3-4 Vol. 409; ISSN 0022-1694; ISSN JHYDA7
- Country of Publication:
- United States
- Language:
- English
Similar Records
An Integrated Hydrologic Bayesian Multi-Model Combination Framework: Confronting Input, parameter and model structural uncertainty in Hydrologic Prediction
Equifinality of formal (DREAM) and informal (GLUE) bayesian approaches in hydrologic modeling?