Prediction of rockhead using a hybrid N-XGBoost machine learning framework

作     者：Xing Zhu Jian Chu Kangda Wang Shifan Wu Wei Yan Kiefer Chiam Xing Zhu;Jian Chu;Kangda Wang;Shifan Wu;Wei Yan;Kiefer Chiam

作者机构：School of Civil and Environment EngineeringNanyang Technological University618798Singapore State Key Laboratory of Geohazard Prevention and Geoenvironment ProtectionChengdu University of TechnologyChengdu610059China Building and Construction Authority200 Braddell Road579700Singapore 

出 版 物：《Journal of Rock Mechanics and Geotechnical Engineering》 (岩石力学与岩土工程学报（英文版）)

年 卷 期：2021年第13卷第6期

页      面：1231-1245页

核心收录：

学科分类：08[工学] 080104[工学-工程力学] 0815[工学-水利工程] 0801[工学-力学（可授工学、理学学位）] 

基　　金：supported by National Research Foundation(NRF)of Singapore,under its Virtual Singapore program(Grant No.NRF2019VSG-GMS-001) by the Singapore Ministry of National Development and the National Research Foundation,Prime Minister’s Office under the Land and Livability National Innovation Challenge(L2 NIC)Research Program(Grant No.L2NICCFP2-2015-1) 

主　　题：Rockhead Machine learning(ML) Probabilistic model Gradient boosting 

摘      要：The spatial information of rockhead is crucial for the design and construction of tunneling or underground *** the conventional site investigation methods(*** drilling) could provide local engineering geological information,the accurate prediction of the rockhead position with limited borehole data is still challenging due to its spatial variation and great uncertainties *** the development of computer science,machine learning(ML) has been proved to be a promising way to avoid subjective judgments by human beings and to establish complex relationships with mega data ***,few studies have been reported on the adoption of ML models for the prediction of the rockhead *** this paper,we proposed a robust probabilistic ML model for predicting the rockhead distribution using the spatial geographic *** framework of the natural gradient boosting(NGBoost) algorithm combined with the extreme gradient boosting(XGBoost)is used as the basic *** XGBoost model was also compared with some other ML models such as the gradient boosting regression tree(GBRT),the light gradient boosting machine(LightGBM),the multivariate linear regression(MLR),the artificial neural network(ANN),and the support vector machine(SVM).The results demonstrate that the XGBoost algorithm,the core algorithm of the probabilistic NXGBoost model,outperformed the other conventional ML models with a coefficient of determination(R2)of 0.89 and a root mean squared error(RMSE) of 5.8 m for the prediction of rockhead position based on limited borehole *** probabilistic N-XGBoost model not only achieved a higher prediction accuracy,but also provided a predictive estimation of the ***,the proposed N-XGBoost probabilistic model has the potential to be used as a reliable and effective ML algorithm for the prediction of rockhead position in rock and geotechnical engineering.