Predictive modelling of strength characteristics of stabilized medium expansive soils

This research explores the use of Artificial Neural Network (ANN) modeling to predict the Unconfined Compression Strength (UCS) of stabilized medium expansive soil, aiming to optimize the parameters influencing soil stabilization. A database comprising 240 data points was compiled from laboratory tests involving seven input parameters: Stabilizers content (SCBA & WMD), Curing Period (CP), Liquid Limit (L.L), Plasticity Index (PI), Specific Gravity (Gs), and Free Swell (FS). ANN modeling, employing Levenberg-Marquardt algorithms, demonstrated successful UCS prediction. Increasing the number of neurons improved model accuracy, with optimum results achieved with 14 neurons. With 14 neurons for LMA, the R and R² value reaches 0.99, 0.98 Moreover, plots between experimental and predicted values shows strong correlation as majority of predicted UCS is closed to line of fit. Also error shows large count of data points closed to line of zero error.
Sensitivity analysis highlighted SCBA, WMD, CP, L.L, and P.I as significant contributors to UCS prediction, emphasizing their importance in soil stabilization. The study underscores the effectiveness of ANN modeling in predicting soil strength and recommends 4% SCBA and 20% WMD for optimal stabilization. Overall, this research presents a comprehensive approach to predicting UCS in stabilized expansive soil, offering insights into parameter optimization and model enhancement for future geotechnical applications.