Spatial prediction of rockhead profile using the Gaussian process regression method

Abstract

The spatial distribution of rockhead profile has a significant impact on the design and construction of geotechnical engineering structures. Limited by the 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 Gaussian process regression (GPR) method is used to predict the rockhead profile. Borehole data from a construction site in Hong Kong are used to evaluate the ability of the GPR method to predict rockhead profile. Besides, the influences of the amount of borehole data on the accuracy of the GPR model and the spatial prediction results of rockhead are investigated. The results indicate that the GPR model based on the square exponential and the Matérn covariance function can obtain more accurate prediction results, and the GPR model with limited borehole data can provide a reasonable prediction interval for rockhead depth. With the increase of borehole data, the generalization ability and prediction accuracy of the GPR model gradually improves. In engineering practice, the prediction accuracy and uncertainty degree of the GPR model can be used to judge whether it is necessary to continue to increase borehole data.

Investigation on the failure mechanism of the collapse of the columnar jointed basalt in underground cavern

“…The structural plane derives the complex properties such as anisotropy and heterogeneity of the surrounding rock, which makes the mechanical behavior of the rock mass much more complex than that of general homogeneous, continuous and isotropic materials (Jin et al, 2014;Xia et al, 2020;Lei et al, 2023;Chen et al, 2024;Zhao et al, 2024a;Zhao et al, 2024b). In essence, the fracture of the CJB is a three-dimensional evolutionary process (Feng et al, 2021;Yang et al, 2021;Deng et al, 2023). To fully understand the mechanical property of rock fracture, highprecision microseismic (MS) monitoring technology is introduced into underground caverns to monitor the fracture process of the CJB (Chen et al, 2014;Han et al, 2023).…”

Stability of unsaturated soil slope considering stratigraphic uncertainty and rotated anisotropy of soil properties

“…To simulate the stratigraphic uncertainty, researchers put forward many methods, such as Poisson process method, coupled Markov chain (CMC) method, Markov random field theory, data-driven approach based on multiple point statistics and Gaussian process regression method. 8 Park et al 9 proposed a generalized CMC model to overcome the limitations of traditional CMC model. Deng et al 10 enhanced the generalized CMC model by proposing an estimation method for horizontal transition probability matrix (HTPM).…”

“…The stability analysis of slopes has recently received increasing attention, with stratigraphic uncertainty and inherent variability of soil properties being taken into account. To simulate the stratigraphic uncertainty, researchers put forward many methods, such as Poisson process method, coupled Markov chain (CMC) method, Markov random field theory, data‐driven approach based on multiple point statistics and Gaussian process regression method 8 . Park et al 9 .…”