Intelligent Prediction of Unconfined Compressive Strength and Young’s Modulus of Lean Clay Stabilized with Iron Ore Mine Tailings and Hydrated Lime Using Gaussian Process Regression

Abstract

Chemical stabilization is used to enhance and increase the strength characteristics of soft and problematic soils. In this research, Gaussian Process Regression (GPR) is employed to estimate the unconfined compressive strength (UCS) and the Young’s modulus (E) of lean clay soils stabilized with iron ore mine tailing (IOMT) and hydrated lime (HL) percentage. In this regard, four inputs including the moisture content (MC), IMOT percentage, HL percentage, and curing time (CT) were used. The value of R2 for estimating the UCS and the E were 0.9825 and 0.9633 for all data, respectively. The RMSE for predicting the UCS and the E were 0.1875 and 19.868 for all data, respectively. The result of the sensitivity analysis demonstrated that MC, CT, HL, and IOMT percentage have the highest contribution to the UCS of the stabilized lean clay, respectively. Also, MC, HL, IOMT percentage, and CT have the highest impact on the E of the stabilized lean clay, respectively. The parametric study also revealed that increasing the HL content and the curing time led to an increase in the UCS and the E of stabilized lean clay, while IOMT content and the moisture content has an inverse relationship with the UCS and the E of stabilized lean clay soils.

Keywords

• lean clay stabilization
• iron ore mine tailing
• hydrated lime
• unconfined compressive strength
• young’s modulus
• gaussian process regression