Case Studies in Construction Materials (Dec 2024)
Comparative study on the prediction of the unconfined compressive strength of the one-part geopolymer stabilized soil by using different hybrid machine learning models
Abstract
With the development of green, low-carbon, and sustainable economic systems, the issues of high pollution and energy consumption in construction materials have become increasingly prominent. This study focuses on adopting one-part geopolymer (OPG) in soil stabilization for underground engineering, which exhibits environmental and low-carbon advantages. The unconfined compressive strength (UCS) serves as a crucial parameter for assessing stabilized soil’s performance. However, it is necessary to conduct a large number of experiments, inducing high costs and time consumption. In this study, one multiple linear regression model, one Decision Tree (DT) model, five ensemble machine learning (ML) models (i.e. Random Forest [RF], Extra Tree [ET], Gradient Boosting [GB], Gradient Boosting Decision Tree [GBDT], and Extreme Gradient Boosting [XGBoost]), and hybrid models of those single ensemble models with Particle Swarm Optimization (PSO) (i.e. PSO-RF, PSO-ET, PSO-GB, PSO-GBDT, and PSO-XGBoost) were adopted and compared to achieve better prediction on the UCS of the OPG-stabilized soil. Furthermore, the interpretable method including SHAP and PDP (1D and 2D), was employed to investigate the precise mechanisms by which input parameters influenced the output label. The results revealed that the multiple linear regression model delivered the lowest accuracy, and PSO-XGBoost and PSO-ET exhibited the best performance on the prediction of the UCS with R2 value of 0.9964 and 0.9928, respectively. In addition, Curing time exerted the most significant impact on the UCS, followed by FA/GGBFS, Molarity, Water/Binder, and NaOH/Precursor. Compared to the SHAP method, the PDP offered a more intuitive approach to reveal the relationship between the inputs and output. The outcome of the study shed new light on the application of ML models in the prediction of the OPG-stabilized soil’s performance in underground engineering.
