Prediction of soil permeability coefficient using the GEP approach

Hydraulic permeability of soil (k) is a critical parameter for mathematical modeling of groundwater and soil water flow. Due to the complexity of k  it is hard to gain a general empirical model which provides a reliable prediction of it. Therefore, this study used the Gene Expression Programming (GEP) model as a powerful data-driven technique for the estimation of k. The available published data for estimation of k  are culled from the literature. Six effective parameters including clay content (CC), water content (ω), liquid limit (LL), plastic limit (PL), specific density (γ), void ratio (e) were used to establish a predictive formula for estimation of k. Statistical parameters such as BIAS, Root Mean Square Error (RMSE), Scatter Index (SI), correlation coefficient (R), and Mean Absolute Error (MAE) were used for evaluating the accuracy of the developed GEP model. In addition, GEP findings were compared to Artificial Neural Network (ANN) to assess the performance of the GEP. The GEP with BIAS = -0.0005, RMSE = 0.0079, SI = 57.33%, R = 0.8109 and MAE = 0.0047 outperformed than ANN with BIAS = 0.001, RMSE = 0.0090, SI = 65.12%, R = 0.7490 and MAE = 0.0053 in predicting k in testing stage. GEP provided explicit mathematical equation can be utilized to determine k. Comparing the observed data and ANN results demonstrated that the GEP approach has suitable performance for prediction of k.