The use of Adaptive Network-based Fuzzy Inference Systems (ANFIS) in event-based rainfall-runoff (R-R) modeling.

Talei A., Chua L.H.C., Quek C., 9th International Conference on Hydroinformatics, 7-10 Sep 2010, Tianjin, China, 2010

This study presents an application of ANFIS in event-based rainfall-runoff modeling. 63 separate rainfall-runoff events from a small urban catchment from singapore were used. Three different approaches were used for selecting the calibration events and the performance of ANFIS R-R models were compared against the physically-based Storm Water Management Model (SWMM). Based on goodness of fit and peak flow comparisons, this study shows that ANFIS results are comparable to SWMM. In addition, ANFIS was found to be better at peak flow estimation compared to SWMM. This study demonstrates the promising potential of neuro-computationally inspired hybrid tools in R-R modeling and analysis.