“…They are mathematical tools that approximate coded simulations of a few well-chosen experiments (Wu et al, 2018). A number of surrogate models can be found in the literature, such as the radial basis function model (Chau et al, 2014), support vector regression (Huang et al, 2015), Kriging (Sacks et al, 1989;Xu et al, 2020), neural networks (Haykin, 1998;Li et al, 2022) and so on. Among them, the Kriging model, also known as Gaussian Process Regression (GPR), is one of the most famous models because it not only has a powerful function representation ability but also can provide an estimation of the model uncertainty.…”