Prediction of Rockhead Depth with Limited Borehole Data: A Yang Chizhong Filtering and Estimation Method

The spatial distribution of rockhead profile has a significant impact on the design and construction of geotechnical engineering structures. Limited by economic and technical conditions, the borehole data of specific sites are often sparse, which brings great challenges to the accurate prediction of rockhead profile. In this study, a Yang Chizhong filtering and estimation method (YCZFEM) is used to predict the rockhead profile. Borehole data from a Hong Kong construction site are studied to illustrate the accuracy and effectiveness of the proposed method. In addition, the influences of the parameters of the model and the amount of borehole data on the spatial prediction results of rockhead are investigated to illustrate the accuracy and effectiveness of YCZFEM. The results indicate that the YCZFEM can provide a reasonable prediction interval for rockhead depth with limited borehole data. With the increase in borehole data, the generalization ability and prediction accuracy of the YCZFEM gradually improves. Furthermore, the accuracy and statistical uncertainty of rockhead predictions by YCZFEM, ordinary kriging, and Gaussian process regression are compared. The results show that YCZFEM has higher accuracy and lower statistical uncertainty compared to the other two widely used methods. Meanwhile, as the number of filtering iterations increases, the filtering curve obtained by YCZFEM becomes smoother, exhibiting characteristics of uniform evolution and phase invariance. Overall, in engineering practice, the prediction accuracy and uncertainty degree of YCZFEM can be used to judge whether it is necessary to continue to increase borehole data.