River Basin Flood Flow Prediction using Adaptive Neuro Fuzzy Inference System (ANFIS)

This paper present the application of a data driven model, Flood Prediction Using Adaptive Neuro – Fuzzy Inference System in forecasting flood flow in Ambica river system ANFIS uses neural network algorithms and fuzzy reasoning to map an input to an output space .The proposed technique combine the learning ability of neural network with the transparent linguistic representation of fuzzy system. Performance of the ANFIS model with selected category and membership function are tested and verified by applying daily rainfall and daily discharge data. Statistical indices such as Root Mean Square Error (RMSE), Correlation Coefficient (R), Coefficient of Determination (R2) and Discrepancy Ratio (D) are used to evaluate performance of the ANFIS models in forecasting flood. This objective is accomplished by evaluating the model by comparing ANFIS model to Statistical method like gamble’s method and Log Pearson type-III method to prediction flood. This comparison shows that ANFIS model can accurately and reliably be used to forecast flood in this study.