Assessing of Groundwater level variation In the hydrogeology issues, is very important. In this research to predicting the groundwater level in Nourabad plain of Lorestan Province, the wavelet neural networks were used and the results compared with artificial neural network. Parameters of precipitation, temperature, flow rate and water level within time period of the previous month were used as input and water table in each period were selected as output through monthly scale (2001-2012). Criterion of correlation coefficient, root mean square error and coefficient of mean absolute error of Nash suttclif were used for evaluating the performance of models. The results showed that the both models are able to estimating the water levels with acceptable level, But in terms of accuracy, wavelet neural network model with the highest correlation coefficient (0.920), the lowest root mean square error (0.074m), mean absolute error (0.048m) and the criterion Nash Sutcliffe (0.835) in validation phase was selected. The results showed that the wavelet neural network model has a great ability in estimating the minimum and maximum values of groundwater level.
Babaali, H., & Dehghani, R. (2018). Comparing the Wavelet Neural Network and Artificial Neural Network Models in Groundwater Level Prediction. Hydrogeology, 2(2), 96-108. doi: 10.22034/hydro.2018.5572
MLA
Hamidreza Babaali; Reza Dehghani. "Comparing the Wavelet Neural Network and Artificial Neural Network Models in Groundwater Level Prediction". Hydrogeology, 2, 2, 2018, 96-108. doi: 10.22034/hydro.2018.5572
HARVARD
Babaali, H., Dehghani, R. (2018). 'Comparing the Wavelet Neural Network and Artificial Neural Network Models in Groundwater Level Prediction', Hydrogeology, 2(2), pp. 96-108. doi: 10.22034/hydro.2018.5572
VANCOUVER
Babaali, H., Dehghani, R. Comparing the Wavelet Neural Network and Artificial Neural Network Models in Groundwater Level Prediction. Hydrogeology, 2018; 2(2): 96-108. doi: 10.22034/hydro.2018.5572
)