Results of application of artificial neural networks in predicting geo-mechanical properties of stabilised clays - A Review

Abbey, Samuel

Abstract

This study presents a literature review on the use of artificial neural networks in the prediction of geo-mechanical properties of stabilised clays. In this paper, the application of ANN in ge-otechnical analysis of clay stabilised with cement, lime, geopolymers and by-product cementi-tious materials has been evaluated. Chemical treatment of expansive clays will involve the de-velopment of optimum binder mix proportions or the improvement of a specific soil property using additives. These procedures often generate large data requiring regression analysis in or-der to correlate experimental data and model the performance of the soil in the field. These analyses involve large dataset and tedious mathematical procedures to correlate the variables and develop required models using traditional regression analysis. The findings from this study show that ANN due to their robust data analysis and correlation capabilities are becoming well known in dealing with the problem of mathematical modeling involving nonlinear functions and have been successfully applied to the stabilisation of clays with high performance. The study also shows that supervised ANN model is well adapted to dealing with stabilisation of clays with high performance as indicated by high R2 and low MAE, RMSE and MSE values. The Le-venberge-Marquardt algorithm is effective in shortening the convergence time during model training.

Citation

Abbey, S. (2021). Results of application of artificial neural networks in predicting geo-mechanical properties of stabilised clays - A Review. Geotechnics, 1(1), 147-171

• Journal Article Type: Review
• Acceptance Date: Aug 11, 2021
• Online Publication Date: Aug 17, 2021
• Publication Date: Aug 17, 2021
• Deposit Date: Aug 11, 2021
• Publicly Available Date: Aug 11, 2021
• Journal: Geotechnics
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 1
• Issue: 1
• Pages: 147-171
• Public URL: https://uwe-repository.worktribe.com/output/7616991