Compression Index Regression of Fine-Grained Soils with Machine Learning Algorithms

Abstract

Soil consolidation, particularly in fine-grained soils like clay, is crucial in predicting settlement and ensuring the stability of structures. Additionally, the compressibility of fine-grained soils is of critical importance not only in civil engineering but also in various other fields of study. The compression index (Cc), derived from soil properties such as the liquid limit (LL), plastic limit (PL), plasticity index (PI), water content (w), initial void ratio (e0), and specific gravity (Gs), plays a vital role in understanding soil behavior. This study employs machine learning algorithms—the random forest regressor (RFR), gradient boosting regressor (GBR), and AdaBoost regressor (ABR)—to predict the Cc values based on a dataset comprising 915 samples. The dataset includes LL, PL, W, PI, Gs, and e0 as the inputs, with Cc as the output parameter. The algorithms are trained and evaluated using metrics such as the coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE). Hyperparameter optimization is performed to enhance the model performance. The best-performing model, the GBR model, achieves a training R2 of 0.925 and a testing R2 of 0.930 with the input combination [w, PL, LL, PI, e0, Gs]. The RFR model follows closely, with a training R2 of 0.970 and a testing R2 of 0.926 using the same input combination. The ABR model records a training R2 of 0.847 and a testing R2 of 0.921 under similar conditions. These results indicate superior predictive accuracy compared to previous studies using traditional statistical and machine learning methods. Machine learning algorithms, specifically the gradient boosting regressor and random forest regressor, demonstrate substantial potential in predicting the Cc value for fine-grained soils based on multiple soil parameters. This study involves leveraging the efficiency and effectiveness of these algorithms in geotechnical engineering applications, offering a promising alternative to traditional oedometer testing methods. Accurately predicting the compression index can significantly aid in the assessment of soil settlement and the design of stable foundations, thereby reducing the time and costs associated with laboratory testing.

Keywords

• compression index
• machine learning
• random forest
• gradient boosting
• AdaBoost