A method to estimate Soil-Water Characteristic Curve for weathered granite soil

Soil water characteristic curve (SWCC) is an important property that should be considered in the analysis of flow in unsaturated soils, the stability analysis due to infiltration of rainfall into slopes, the prediction of other unsaturated properties, etc. Therefore, in this study, we intended to obtain more accurate SWCC by measuring the volume change of the specimen in the SWCC tests. Thus we were able to grasp the change of void ratio during the SWCC tests. Additionally, a method reasonably predicting the SWCC for Korean weathered granite soils was suggested, based on the test results obtained from the experiments conducted in this study. In other words, a method to estimate the parameters used in Fredlund and Xing's equation was proposed using an ANN (artificial neural network). The particle size distribution, compacted water content and void ratio were used as input data in the ANN model for predicting the parameters, since it was confirmed that these basic soil properties have a relationship with the parameters obtained from the test results and the fitting results. The network model connection weights and biases presented in this study produced reliable predictions, and the precision of the prediction results from the proposed method was high, in comparison with the prediction results of other prediction methods.