Prediction of California Bearing Ratio of nano-silica and bio-char stabilized soft sub-grade soils using explainable machine learning

Abstract

This study investigates the prediction of the California Bearing Ratio (CBR) for nano-silica and bio-char stabilized soft sub-grade soils using explainable machine learning (ML) models. The research involves experimentally determining CBR values for soft sub-grade soils treated with varying proportions of nano-silica and bio-char. This data, along with soil properties such as grain size distribution, moisture content, and nano-silica and bio-char content, serve as inputs for training and testing various ML models. Among the 12 ML models evaluated, the Gradient Boosting Regression exhibits superior performance, achieving high accuracy (R² = 0.92) and low error rates (MSE = 0.45). The utilization of explainable artificial intelligence (XAI) techniques provides insight into the significant input features influencing CBR predictions, thereby enhancing the interpretability and reliability of the models.. The research findings, highlight the efficacy of machine intelligence in accurately predicting the CBR values of nano-silica and bio-char stabilized soft sub-grade soils. This research has significant implications for geotechnical engineering, offering a data-driven methodology to optimize soil stabilization practices and contribute to sustainable infrastructure development.