Modelling of geotechnical problems using soft computing

Abstract

Correlations are very significant from the earliest days; in some cases, it is essential as it is difficult to measure the amount directly, and in other cases it is desirable to ascertain the results with other tests through correlations. Soft computing techniques are now being used as alternate statistical tool, and new techniques such as artificial neural networks (ANN), support vector machine (SVM), multivariate adaptive regression splines (MARS) has been employed for developing the predictive models to estimate the needed parameters. In this report, four geotechnical problems like compaction parameters of sandy soil, compression index of clay, relative density of clean sand and side resistance of drilled shaft have been modeled. Various error criteria such as mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) and correlation coefficient (R) have been considered for the comparison of different models. Finally different sensitivity analysis has been shown to identify the significance of different input parameters that affects the developed models. The performance comparison showed that the soft computing system is a good tool for minimizing the uncertainties in the soil engineering projects. The use of soft computing may provide new approaches and methodologies to minimize the potential inconsistency of correlations.