Soft computing is an innovative approach to construct computationally intelligent systems that are supposed to possess humanlike expertise within a specific domain, adapt themselves and learn to do better in changing environments and explain how they make decisions. The application of neural network and fuzzy logic techniques as modeling tools are growing in the field of hydrology. In the present study Artificial neural network (ANN), Mamdani fuzzy inference systems (MFIS) andAdaptive Neuro Fuzzy (ANFIS) was used to predict the groundwater levels of Thurinjapuram watershed, Tamilnadu. Antecedent rainfall and water levels are taken as inputs, and the future water level is an output. In this study, 25 years of water level data were analyzed. The analysis of the three models is performed by using the same input and outputvariables. The models are evaluated using three statistical performance criteria namely Mean Absolute Percentage Error, Root Mean Squared Error and Regression coefficient. For performance evaluation, the model predicted output was compared with the actual water level data. Simulation results reveal that ANFIS is an efficient and promising tool.
[1]
Karim Solaimani,et al.
Rainfall-runoff prediction based on artificial neural network (a case study: Jarahi watershed).
,
2009
.
[2]
Gorjan Alagic,et al.
#p
,
2019,
Quantum information & computation.
[3]
N. Mondal,et al.
Deciphering potential groundwater zone in hard rock through the application of GIS
,
2008
.
[4]
Markus Disse,et al.
Fuzzy rule-based models for infiltration
,
1993
.
[5]
Stefano Alvisi,et al.
Water level forecasting through fuzzy logic and artificial neural network approaches
,
2005
.
[6]
Shakeel Ahmed,et al.
Forecasting groundwater level using artificial neural networks.
,
2009
.