Hydraulic conductivity prediction based on grain-size distribution using M5 model tree

The hydraulic conductivity, K_s, is one of the most important hydraulic properties which controls the water and solute movement into the soil. It is measured on soil specimens in the laboratory. On the other hand, sometimes it is obtained by tests carried out in the field by a number of researchers. Therefore, several experimental formulas have developed to predict it. Recently, soft computing tools have been used to evaluate the hydraulic conductivity. However, these tools are not as transparent as empirical formulas. In this study, another soft computing approach, i.e. model trees, have been used for predicting the hydraulic conductivity. The main advantage of model trees is that, unlike the other data learning tools, they are easier to use and represent understandable mathematical rules more clearly. In this paper, a new formula that includes some parameters is derived to estimate the hydraulic conductivity. To develop the new formulas, experimental data sets of hydraulic conductivity were used. A comparison is made between the estimated hydraulic conductivity by this new formula and formulas given by other’s researches.