Evaluation of Untreated and Treated Coir Geotextile Performance under Cyclic Loading on Unpaved Roads

This study investigates the cyclic loading behaviour of a two-layered unpaved road model reinforced with untreated/treated woven and non-woven coir geotextiles over 10,000 cycles. In this study, research efforts were made to develop artificial-neural-network (ANN)-based prediction models for the plastic deformation of untreated/treated coir geotextile-reinforced unpaved road models. Pearson's coefficient of correlation (R²) and the root mean square error (RMSE) was utilized to evaluate the predictive accuracy of the predictive models. Key discoveries include a substantial reduction in plastic deformation for the reinforced two-layered unpaved road models (Types W1, W2, NW1, and NW2), showcasing decreases of 69%, 74%, 58%, and 66%, respectively, compared to the unreinforced model, particularly in unsoaked conditions. The results demonstrated reduction in the plastic deformation in treated coir geotextiles reinforced models. The study reveals an escalation in plastic deformation at 60% cyclic load as opposed to 30%, evident in both unsoaked and soaked conditions. The selected neural network model exhibits high accuracy, with R² values exceeding 0.95 and RMSE values below 1, indicating precise prediction of plastic deformation of untreated/treated coir geotextile-reinforced unpaved road model.