ANN and Fuzzy Logic Models for the Prediction of groundwater level of a watershed

Computational Intelligence techniques have been proposed as an efficient tool for modeling and forecasting in recent years and in various applications. Groundwater is a highly valuable resource. Measurement and analysis of groundwater level is needed for maintaining groundwater availability. It is therefore necessary to implement mechanisms and systems that can be employed to predict the groundwater level. The primary objective of this paper is to compare the efficiency of two computational intelligence techniques in groundwater level prediction of a watershed. The techniques under comparison are Artificial Neural Networks (ANNs) and Fuzzy Logic (FL). A three-layer feed-forward ANN was developed using the sigmoid function and the back propagation algorithm. The FL model was developed employing the Gaussian fuzzy membership functions for the input and output variables. The fuzzy rules were inferred from the measured data. In this study it was observed that ANNs perform significantly better than FLs. This performance is measured against the generalization ability of the two techniques in groundwater level prediction of a watershed. KeywordsArtificial Neural Networks, Fuzzy logic, Mamdani fuzzy inference systems, Groundwater level, MATLAB, Observation wells.