“WATER QUALITY MODELING OF RIVER WATER BY USING ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM”

Abstract

COD and DO is a parameter frequently used to evaluate the water quality of different rivers. The aim of the present
study is to investigate applicability of artificial intelligence techniques such as ANFIS (Adaptive Neuro-Fuzzy Inference
System) in water quality COD and DO prediction for the case study, TAPI river basin of MAHARASHTRA, India. The
proposed technique combines the learning ability of neural network with the transparent linguistic representation of fuzzy
system. ANFIS models with various input structures and membership functions are constructed, trained and tested to evaluate
efficiency of the models. For DO and COD we use past data of 5 years and various parameters uses are Ph, Temperature,
Electrical Conductivity, Suspended solids 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
predicting COD and DO. ANFIS model is used for the estimation of COD and DO concentration.