Coefficient of permeability prediction of soils using gene expression programming

Abstract

The coefficient of permeability is the most important parameter for characterizing the permeability characteristics of soil. In this study, a database of the coefficient of permeability (k) for soils was compiled firstly, including effective size (d10), mean grain size (d50), the particle diameters at the cumulative percent content of 60% (d60) and void ratio (e), which can reflect the impact of the particle size distribution characteristics. Gene expression programming (GEP), was employed to develop a predictive equation of k, which is convenient for engineering application. The GEP model was compared with eight empirical models and other artificial intelligence models (i.e., random forest (RF) and group method of data handling (GMDH)). The results show that the GEP model and RF model have the highest accuracy, followed by GMDH model and empirical models. Then, the sensitivity analysis was conducted. According to the results, k increases with increasing d10, d50 and e; the effective size d10 has the largest influence on k, followed by d50 and e, which indicates that fine particle content has the control effect on seepage and the effect of soil gradation parameters on k is greater than that of void ratio. Additionally, the SHAP and PDP analysis were conducted to investigate the feature importance and conditional expectation of each feature. The feature importance order is d10 > d50 > e > d60, and the SHAP values of d10, d50 and e increase with the increase of them, while the SHAP value of d60 is basically unchanged.