Estimation of Shear Strength Parameters of Lateritic Soils Using Artificial Neural Network

Abstract

This research work seeks to develop models for predicting the shear strength parameters (cohesion and angle of friction) of lateritic soils in central and southern areas of Delta State using artificial neural network modeling technique. The application of these models will help reduce cost and time in acquiring geotechnical data needed for both design and construction in the study area. A total of eighty-three (83) soil samples were collected from various locations in Delta State of Nigeria. The geotechnical soil properties were determined in accordance with British Standards. The range of the angle of internal friction and cohesion obtained from the tests are 2 to 43 degrees and 3 to 82 kN/m 2 respectively. The optimum artificial neural network architecture network was found to be 3-9-1, that is three inputs, nine hidden layer nodes, and one output node for cohesion. While, the angle of friction had an optimal network geometry of 3-11-1, that is three inputs, eleven hidden layer nodes, and one output node. The results of the coefficient of determination and root mean square showed that the artificial neural network method outperforms some selected empirical formulae in the prediction of shear strength parameters.

Advanced prediction of soil shear strength parameters using index properties and artificial neural network approach

“…Bishoftu, situated in the Oromia Region, is renowned for its distinct geological features, including a variety of soil types, notably Vertisols, which are key to this study [9,29]. The region's geographical setting in the Great Rift Valley, coupled with its varied topography and climate, presents a unique opportunity to study the soil's behaviour under different conditions [10,17]. The town's proximity to Addis Ababa, diverse land use, and presence of crater lakes add to its geotechnical interest, making it an ideal location for investigating soil shear strength parameters using advanced techniques like Artificial Neural Networks (ANN) [1,6].…”

“…These parameters are indispensable for foundation analysis and the stability of various structures. Traditional methods to determine these parameters, such as direct shear and triaxial compression tests, are often costly and labor-intensive [9,10]. They also face challenges in acquiring accurate soil samples, particularly in developing countries.…”

The Particle Size Distribution of Laterite Soil at Ekosodin, Benin City, Nigeria

“…Soil Sampling: A total of hundred soil samples were collected from Ekosodin area. The sample size was decided based on the range of sample sizes recommended from similar research (Surendra and Gurcharan, 2014;Purwana and Nikraz, 2014;Iyeke, et al, 2016). The soil was sampled at a 1.5m depth below the earth surface with the use of a hand auger.…”

Estimation of Shear Strength Parameters from Easily-Collected Soil Physical Properties Using Bagging Learning Technique

“…Consequently, the predicting results of the RF exhibits higher accuracy compared to the empirical equations, which were obtained from linear regression method. This method relies on the assumption of linearity between the features, which can potentially yield less accurate results (Iyeke et al, 2016). Furthermore, this approach can lead to excessive similarities between an analysis and a dataset, potentially resulting in the failure to generate reliable predictions and accurately forecast future observations.…”

“…With the advent and widespread application of machine learning (ML) in addressing engineering challenges, it has become a valuable tool for handling big data and complex conditions. Numerous studies have emerged utilizing ML techniques to predict shear strength of soil, employing a range of algorithms, most notably Artificial Neural Networks (ANN) (Zhu et al, 2022;Chao et al, 2021;Pham et al, 2018;Iyeke et al, 2016;Khanlari et al, 2012;Mohammadi et al, 2022;Zakharov et al, 2022). Besides the ANN model, Support Vector Machine (SVM) is also a popularly used technique for estimating the shear strength of soil (Zhu et al, 2022;Chao et al, 2021;Pham et al, 2018).…”