An intelligent approach for predicting the strength of geosynthetic-reinforced subgrade soil

In the recent times, use of geosynthetic-reinforced soil (GRS) technology has become popular for constructing safe and sustainable pavement structures. The strength subgrade is routinely assessed in terms its California bearing ratio (CBR). However, past, no effort was made to develop a method evaluating CBR reinforced soil. main aim this paper explore appraise competency several intelligent models such as artificial neural network (ANN), least median squares regression, Gaussian processes elastic net regularisation lazy K-star, M-5 model trees, alternating trees random forest estimating For this, all were calibrated validated using reliable pertinent historical data. prognostic veracity tools mentioned supra well-established traditional statistical indices, external evaluation technique, multi-criteria assessment approach independent experimental dataset. Due overall excellent performance ANN, converted into trackable functional relationship estimate Finally, sensitivity analysis performed find used parameters on value.