Prediction of pullout interaction coefficient of geogrids by extreme gradient boosting model

• Published in: Geotextiles and geomembranes Vol. 50; no. 6; pp. 1188 - 1198
• Main Authors: Pant, Aali, Ramana, G.V.
• Format: Journal Article
• Language: English
• Published: Essex Elsevier Ltd 01.12.2022; Elsevier BV
• Subjects: Algorithms; Coefficients; Extreme gradient boosting; Geogrid; Geogrids; Graphical user interface; Laboratory tests; Machine learning; Mathematical models; Model accuracy; Normal stress; Predictions; Pull out tests; Pullout resistance; Random forest; Testing; Random forest; Extreme gradient boosting; Pullout resistance; Geogrid; Machine learning
• DOI: 10.1016/j.geotexmem.2022.08.003
• ISSN: 0266-1144

Geogrids embedded in fill materials are checked against pullout failure through standard pullout testing methodology. The test determines the pullout interaction coefficient which is critical in fixing the embedment length of geogrids in mechanically stabilized earth walls. This paper proposes prediction of pullout interaction coefficient using data driven machine learning regression algorithms. The study primarily focusses on using extreme gradient boosting (XGBoost) method for prediction. A data set containing 220 test results from the literature has been used for training and testing. Predicted results of XGBoost have been compared with the results of random forest (RF) ensemble learning based algorithm. The predictions of XGBoost model indicates 85% accuracy and that of RF model shows 77% accuracy, indicating significantly superior and robust prediction through XGBoost above RF model. The importance analysis indicates that normal stress is the most significant factor that influences the pullout interaction coefficients. Subsequently pullout tests have been performed on geogrid embedded in four different fill materials at three normal stresses. The proposed XGBoost model gives 90% accuracy in prediction of pullout interaction coefficient compared to laboratory test results. Finally, an open-source graphical user interface based on the XGBoost model has been created for preliminary estimation of the pullout interaction coefficient of geogrid at different test conditions. •This study applies machine learning algorithms for prediction of pullout interaction coefficient of geogrids.•Ensemble learning algorithms have been used on 220 laboratory pullout test results.•Laboratory pullout tests have also been conducted and results have been compared with predicted results for verification.•Open-source graphical user interface has been developed for predicting interaction coefficient values.