Improving the prediction of soil compaction parameters using machine learning models
Improving the prediction of soil compaction parameters using machine learning models
This study aims to enhance the predictive accuracy of fundamental soil compaction parameters, specifically maximum dry density and optimum moisture content, through the application of machine learning models. To achieve this, Random Forest (RF), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Gradient Boosting (GB) algorithms were employed, coupled with advanced validation techniques using cross-validation approach, utilizing a pre-existing dataset from the literature. This investigation highlights the inherent biases associated with the validation methods employed in the baseline study. Furthermore, the findings demonstrate a notable enhancement in both the accuracy and reliability of predictions, highlighting the efficacy of the proposed methodology.
Zakaria Matougui; A. Medjnoun; Lynda Djerbal; Ramdane Bahar
18th African Regional Conference on Soil Mechanics and Geotechnical Engineering (ARCSMGE2024)
Behavior of soils, analysis and modeling
Contact Information
- Secretary General - Dr A M McNamara
- Email: [email protected]
- Phone: +44 20 7040 8154
- City, University of London
- Northampton Square
- London EC1V 0HB. United Kingdom