Exploring the Potential of Machine Learning in Predicting Soil California Bearing Ratio Values
Abstract
Accurately predicting the California Bearing Ratio (CBR) of soil is vital for civil engineering projects as it determines soil strength and stability, crucial for designing safe and durable infrastructure. Conventional methods for calculating CBR values are both expensive and time-consuming, prompting the need for more efficient approaches. This study explores the use of advanced machine learning (ML) techniques to improve workflow and productivity in CBR prediction. Specifically, the Improved Arithmetic Optimization Algorithm (IAOA) and the Bonobo Optimization Algorithm (SBOA) are applied to enhance the Stochastic Gradient Boosting Regression (SGBR) model for predicting CBR values. The SGBR model, known for its ability to handle complex datasets and nonlinear interactions, is optimized to improve predictive accuracy. Performance metrics such as the coefficient of determination (R2), n10-index, and Root Mean Squared Error (RMSE) are used to assess the model's performance. After training, testing, and validation with relevant data, the optimized SGIA model (SGBR enhanced by IAOA) achieves impressive results, including an n10-index of 1.000, a root mean square error of 0.161, and an R2 value of 0.981. These metrics demonstrate the SGIA model's capability to accurately forecast CBR values, offering a reliable, cost-effective alternative to traditional methods for soil evaluation in engineering applications.
Keywords:
regression analysis, California bearing ratio, stochastic gradient boosting regression, self-adaptive bonobo optimization algorithm, improved arithmetic optimization algorithmPublished Online
How to Cite
Issue
Section
License
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see The Effect of Open Access). As soon as the paper is accepted, finally submitted and edited, the paper will appear in the "OnlineFirst" page of the journal, thus from this point no other internet-based publication is necessary.

