Application of the Artificial Neural Network and Neuro-fuzzy System for Assessment of Groundwater Quality

作者：Khaki Mahmoud^*; Yusoff Ismail; Islami Nur

来源：Clean-Soil Air Water, 2015, 43(4): 551-560.

DOI：10.1002/clen.201400267

• ANFIS
• Hydrologic analyses
• Modeling
• Monitoring
• Water resources systems

One of the most important aspects of the evaluation of any aquatic system is the simulation of water quality parameters. Recently, artificial intelligence methods have been broadly applied to simulate hydrological processes. This study evaluates the potential of applying the neuro-fuzzy system and neural network to simulate total dissolved solid and electrical conductivity levels, by employing the values of other existing water quality parameters. Consideration of these results will be important for implementing and adopting a water quality prediction model which is able to provide a useful tool for the management of water resources. In this study, water quality data were analyzed from five sampling stations over six years from 2008 to 2013, in the Langat Basin, Malaysia. An assessment of the model's performance was carried out through the correlation coefficient and mean squared error obtained from the model computation and measurement values of the dependent variables. Consequently, a close agreement between these values and their respective measured values in the quality of the groundwater were found. Accordingly, artificial intelligence approaches and adaptive neuro-fuzzy inference system models in particular are capable of interpreting the behavior of water quality parameters.

• 出版日期2015-4