ABSTRACT
An Adoption of a good estimation model for the prediction of sub soils properties before the commencement of a construction project, or at the preliminary stage of project planning is highly imperative. This will mitigate the most unexpected costs incurred during construction which are mostly geotechnical in nature. This study used Machine Learning (ML) techniques such as: Multiple Linear Regression (MLR), Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF), and M5 Tree (M5P) to link the experimentally determined index properties of optimum moisture content (OMC), maximum dry density (MDD), soaked California bearing ratio (SCBR), and unsoaked California bearing ratio (USCBR). Four Hundred and Eighty (480) soil samples in Ekiti State were subjected to Geotechnical and Geo-chemical tests. R studio Software version 1.2.5033 has been used to develop Machine Learning (ML) models for the ANN, RF, MSP, MLR, and SVM techniques in terms of Natural Moisture Content. Predictive models were created based on the experimental data., liquid limit (π€πΏ), plasticity index (πΌπ) and percentage of fines, Gravel, and Sand respectively. Arch GIS software was used to develop the Soil Base Map. The results from index properties classified the soils of the study area as A-2-4, A-2-6, A-2-7 and A-7-5 for Ekiti Central Senatorial Districts (ECSD) and A-2-4, A-2-5, A-2-6, A-2-7, A-4, A-5, A6 and A-7- 5 for Ekiti South Senatorial Districts ( ESSD) while Ekiti Northern Senatorial Districts (ENSD) were classified as A-2-4, A-2-5, A-2-6, A-2-7, A-6 and A-7-6. The strengths of the developed Machine Learning models have been examined in terms of regression coefficient (R2 ) and Root Mean Square Error (RMSE) values. It was found that all the five ML models predict OMC, MDD, SCBR and USCBR close to the experimental value. However, the prediction of OMC, MDD, SCBR and USCBR by RF was found better than other ML models deployed in this research.
