ESTIMATION OF SHEAR STRENGTH OF SOIL USING MACHINE LEARNING TECHNIQUE

Abstract

Shear strength is a significant criterion used to determine the capability of ground foundation in the design phase of many megaprojects (highways, roads, high-rise buildings) and geotechnical constructions (earth dams, retaining walls). These characteristics are determined through laboratory testing. Because shear strength have such a strong influence on soil carrying capacity, a great number of experimental and theoretical investigations have been conducted to better understand soil strength behaviours. This study focuses on the creation of machine learning models such as Artificial Neural Network(ANN) Multilayer Perceptron(MLP) and Radial basis Function(RBF) for predicting shear strength of soil using data from TC304 Database. For estimating shear strength, relevant input factors such as Undrained shear strength (USS), vertical effective stress (VES), preconsolidation stress (ps), liquid limit (LL), plastic limit (pl), and natural water content are all metrics in two datasets have been chosen. The most essential variables for predicting soil shear strength using the ML model were determined to be vertical effective stress, pre - consolidation stress, depth, and plastic limit. The effectiveness of the ANN model was assessed using well-known statistical metrics like the mean absolute error (MAE), root mean squared (RMSE), and coefficient of correlation (R). The proposed models were able to learn the intricate relationship between soil strength and their contributing factors effectively.