Prediction of Undrained Shear Strength by the GMDH-Type Neural Network Using SPT-Value and Soil Physical Properties

Abstract

This study presents a novel method for predicting the undrained shear strength (cu) using artificial intelligence technology. The cu value is critical in geotechnical applications and difficult to directly determine without laboratory tests. The group method of data handling (GMDH)-type neural network (NN) was utilized for the prediction of cu. The GMDH-type NN models were designed with various combinations of input parameters. In the prediction, the effective stress (σv’), standard penetration test result (NSPT), liquid limit (LL), plastic limit (PL), and plasticity index (PI) were used as input parameters in the design of the prediction models. In addition, the GMDH-type NN models were compared with the most commonly used method (i.e., linear regression) and other regression models such as random forest (RF) and support vector regression (SVR) models as comparative methods. In order to evaluate each model, the correlation coefficient (R2), mean absolute error (MAE), and root mean square error (RMSE) were calculated for different input parameter combinations. The most effective model, the GMDH-type NN with input parameters (e.g., σv’, NSPT, LL, PL, PI), had a higher correlation coefficient (R2 = 0.83) and lower error rates (MAE = 14.64 and RMSE = 22.74) than other methods used in the prediction of cu value. Furthermore, the impact of input variables on the model output was investigated using the SHAP (SHApley Additive ExPlanations) technique based on the extreme gradient boosting (XGBoost) ensemble learning algorithm. The results demonstrated that using the GMDH-type NN is an efficient method in obtaining a new empirical mathematical model to provide a reliable prediction of the undrained shear strength of soils.

Analysis and prediction of surface settlements during the digging of underground mining works (Algeria)

“…By agreeing with the empirical correlations and studies proposed for the determination of soil properties on the basis of standard penetration test values and the pressuremeter test [9,10] and their comparison with those obtained in the labo ratory to characterize the geotechnical units, the materials crossed by the tunnel are clayey silts, slightly marly to marly taking into account the USCS system (Unified Soil Classifica tion System).…”

Deep Learning Approach on Prediction of Soil Consolidation Characteristics

“…As the field continues to explore more applications of AI, new techniques will be developed to more effectively address these challenges. It is evident that the utilization of computer science and AI in geotechnical engineering, as well as in other fields, will continue to expand and generate interest [9][10][11][12][13][14][15].…”

Prediction of the Undrained Shear Strength of the Remolded Soil with Non-Linear Regression, Fuzzy Logic and Artificial Neural Network

“…Similar results have been reported bySharma and Bora (2003) andYasun (2018) Kayabaşı and Gökçeoğlu 2018;Demir and Şahin 2022),. shallow and deep foundation(Moayedi and Hayati 2019;Liu et al 2020;Mbarak et al 2020;Moayedi et al 2020;Zhang et al 2021;Armaghani et al 2022), soil and pavement(Işık 2009;Kalkan et al 2009;İkizler et al 2010;Akan and Keskin 2019;Dehghanbanadaki et al 2019;Taleb Bahmed et al 2019;Abu-Farsakh and Mojumder 2020;Kayabaşı 2020;Zhai et al 2020;Akbay Arama et al 2021;Tabarsa et al 2021;Kim et al 2022;Lin et al 2022;Tran et al 2022;),…”