A Review of Bayesian Model Averaging Approach for Urban Drainage Water Quality Modeling

The uncertainty in urban drainage water quality modeling is highly relevance in any practical application. Several models are available in the literature for such tasks, and one of the most problematic choices is the selection of the most appropriate approach for the specific application. The Bayesian Model Averaging approach attempts to support the modeler in such choices by providing a method to identify and select the best performing models and average their output response to reduce the related uncertainty. In the current report, the Bayesian Model Averaging is proposed and discussed. The method is one of the most promising uncertainty-based model selection tool and it is able to improve the selection of the most appropriate model for a specific case once new knowledge is available. The method is theoretically discussed and conclusions on possible application are drawn.