Soil-Water Characteristic Curve prediction by Gene Expression Programming

Soil–water characteristic curve is one of the most important parts of any model that describes unsaturated soil behavior as it explains the variation of soil suction with changes in water content. In this research, gene expression programming is employed as an artificial intelligence method for modelling of this curve. Geneexpression programming can operate on large quantities of data in order to capture nonlinear and complexrelationships between variables of the system. Inputs of the model are the initial void ratio, initialgravimetric water content, logarithm of suction normalized with respect to atmospheric air pressure, clay content, and silt content. The model output is the gravimetric water content corresponding to the assigned input suction. The results illustrate that the advantages of the proposed approach are highlighted

Keywords:

Unsaturated soil , Soil–water characteristic curve , Pressure plate test , Gene expression programming