Adaptive neuro-fuzzy inference system for intelligent water quality classification in Tilesdit dam from Algeria

This paper presents the application of an Adaptive Neuro-Fuzzy Inference System (ANFIS) in classification of water quality status. ANFIS is one of the useful and powerful neural network approaches for the solution of pattern recognition problems in the last decades. This study involved the evaluation and interpretation of surface water quality data in Tilesdit dam from Algeria. It also allowed us to obtain more advanced information about water quality, and to design a monitoring network for this study area. The ANFIS which is a technique for pattern classification has been widely used in many application areas such as water quality monitoring. This method is a binary classification technique, but in some cases, such as pattern recognition, we need more than two classes. A multi-class problem using ANFIS is a typical example for solving the mentioned problem. In this work, four physicochemical parameters in 4 seasons during the period 2009-2011, located at Tilesdit dam, were selected for this study, such as pH, Temperature, Conductivity and Turbidity to supervise water quality. Up to 95 % of the data could be correctly classified using ANFIS model. Its performance is more competitive when compared with artificial neural networks. Furthermore, the results demonstrated that the proposed procedure has a great potential in water quality monitoring.