ABSTRACT The Compression index, known as Cc, plays a crucial role in geotechnical design. However, the conventional approach to ascertain Cc is not only expensive but also time-intensive. This paper proposes an innovative modeling approach to develop a Deep Neural Network (DNN)-based formula for the prediction of Cc incorporating readily accessible physical properties of soil, including specific gravity (G), saturation degree (Sr), liquid limit (LL), silt content (SC), and clay content (CC). To assess the predictive performance of the proposed formula, various metrics were employed, such as determination coefficient (R²), root mean square error (RMSE), mean absolute error (MAE), and Nash–Sutcliffe Efficiency (NSE). From the collected dataset, 608 samples were used as the training set for the DNN model, while the remaining 152 samples were designated as the testing set. The R², RMSE, MAE, and NSE values for the training and testing sets were 0.9821 and 0.9935; 0.126 and 0.098; 0.083 and 0.074; 0.9812 and 0.9922, respectively. These results indicate that the developed equation demonstrates outstanding predictive accuracy for estimating Cc. Furthermore, the comparative analysis underscores that the proposed DNN-based formula significantly outperforms empirical equations and multilinear regression (MLR) model in predicting Cc with higher accuracy.
Read full abstract