Search

Adoption of a good estimation model for the prediction of subsoils 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 research aims to use Machine Learning (ML) tools such as Multiple Linear Regression(MLR)Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF) and M5 Tree (M5P) in geotechnical Engineering with a view to correlate Optimum Moisture Content (OMC),Maximum Dry Density (MDD) and Soaked California Bearing Ratio (SCBR) and Unsoaked California Bearing Ratio (USCBR) from the laboratory by conducting tests on 480 disturbed soil samples The principal component analysis (PCA) was used to examine Collinearity problem among the data set. The actual and predicted values of the machine learning (ML) models using root mean square error (RMSE) showed a varied values of RMSE and Coefficient of determination (R2). The results varied between 0.04 -0.92 and 0.02 - 0.93 for OMC and MDD while SCBR and UNSCBR ranges from 0.16 to 0.94 and 0.01 to 0.92 f respectively. From the fore going RF gave the least values of RMSE as 101.63 and 1.67 and the highest value of R2 as 0.92 and 0.93. The results showed that these models had R2 values greater than 90% and the variation of error between the observed and the predicted values of estimated geotechnical parameters was less than ±2. It's concluded that these models will be useful for preliminary design of Civil engineering infrastructure in Ekiti-State, South Western, Nigeria. [ABSTRACT FROM AUTHOR]

This research seeks to evaluate the geo chemical classification of Ekiti State Soils and examine its suitability for road works the study area was divided into three districts thus: Ekiti Central Senatorial Districts (Ekiti Southern Senatorial Districts (ESSD) and Ekiti Northern Senatorial Districts (ENSD). A total of 480 samples were obtained with 160 samples from per districts. Laboratory tests such as Chemical and Geotechnical test were analyzed. The results showed that soil index properties classified the soils of the ECSD into four classes as A-2-4, A-2-6, A-2-7 and A-7-5, the ESSD into Eight as A-2-4, A-2-5, A-2-6, A-2-7, A-4, A-5, A-6 and A-7-5 while ENSD were classified into Six classes as A-2-4, A-2-5, A-2-6, A-2-7, A-6 and A-7-6 respectively. The chemical test showed ECSD has the purest, finest and most economically valuable clay mineral among others and also grouped the districts soils into three classes as: Laterite soil, Lateritic soil and non-Lateritic soil. It is concluded that the soils found in the study area are adequate for Civil engineering works particularly samples from ECSD while other districts will also be adequate if treated with additives to improve their geotechnical properties. [ABSTRACT FROM AUTHOR]

Application of Machine learning which is the main driver of Artificial Intelligence is gradually gaining ground in the field of geotechnical engineering for prediction and forecasting. In the present research, efforts are made to explore some machine learning techniques such as: Support Vector Machine, Random Forest, Artificial Neural Networks, M5 Tree and Multiple Linear Regression models to correlate maximum dry density and optimum moisture content with some soil index properties where the best predicting model was determined. Four hundred and eighty (480) soil samples were obtained and divided into data set using training and validation of the developed models from the basic soil parameters. The Goodness of fit between the Actual and the Predicted Values showed that the values of Root Mean Square Error 253.84, 295.44, 218.08, 101.63, 211.12 and 3.91, 4.55, 3.54, 1.67, 20.13. are from Support Vector Machine; Random Forest, Artificial Neural Networks, M5 Tree and Multiple Linear Regression models for Maximum Dry Density and Optimum Moisture Content values respectively. The least values 101.63 and 1.67 was observed from Random Forest for Maximum Dry Density and Optimum Moisture Content. Similarly, the correlation coefficient values range between 0.15 - 0.96 and 0.2 - 0.96. From the foregoing, the correlation coefficient value proved the Random Forest model as the best for estimating Maximum Dry Density and Optimum Moisture Content while the model having the least correlation coefficient is the Multiple Linear Regression model for Maximum Dry Density and Support Vector Machine for Optimum Moisture Content respectively. It's concluded that this research work will be an excellent guide to Constructors, Future planners and Civil engineers for estimation of unavailable data, and for cross checking the observed values particularly at the project preliminary stages within the study area. [ABSTRACT FROM AUTHOR]

Machine learning techniques such as the Support Vector Machine (SVM), Random Forest (RF), M5 tree, Multiple linear regression and Artificial Neural Network was adopted to correlate soil physical parameters and California Bearing Ratio (CBR) of soils for Soaked (SCBR) and Unsoaked (USCBR). Four hundred and eighty (480) soil samples were obtained and divided into data set using training and validation of the developed models from some basic soil parameters. Principal Component Analysis (PCA) was implemented to reduce the large dimension of the data set an the actual and predicted values from the models using Root Mean Square Error (RMSE) and coefficient of determination R², it showed RMSE as 21.6, 21.23, 295.67, 7.03, 14.54 and 24.43,24.59,326.49,8.63,17.71 are from; MLR, ANN, MS Tree, RF, and SVM model for SCBR and USCBR values respectively. The least values 7.03 and 8.63 were observed from random forest (RF) for SCBR and USCBR. Similarly, the R values ranges between 0.1 - 0. 94 and 0.01 - 0.92 which established the relationship among the predicted and the actual SCBR and USCBR. The correlation coefficient values showed the Random Forest Model for SCBR and USCBR as the best, while the model having the least coefficient of determination R² is the MS tree model for both SCBR and USCBR respectively. [ABSTRACT FROM AUTHOR]