Simulation of Cross-Correlated Random Fields for Transversely Anisotropic Soil Slope by Copulas

Multi-source uncertainties yielded by randomness, spatial variability and cross-correlation of soil parameters severely affect the realization of random fields. However, current studies rarely account for these simultaneously, leading to inevitable bias in random field simulation and subsequent structure analysis. In this paper, copula-based cross-correlated random fields for transversely anisotropic soil slope are proposed. Firstly, based on the traditional probabilistic method and random field theory, the effect of the cross-correlation of soil parameters on the random field is comprehensively analyzed. Then copulas, which mainly characterize the dependent structures of random variables, are further expanded to connect multivariate random fields. Four special algorithms associated with Gaussian, Frank, Plackett and No. 16 copulas are subsequently developed. At last, the performance and effectiveness of copula-based cross-correlated random fields are illustrated by means of assumed and engineering slope cases. The results show that the proposed method is amenable to characterizing spatial variability comprising multiple cross-correlated soil parameters of transversely anisotropic slope. Soil profiles can be represented with a relatively high accuracy. Moreover, the performance of copula-based CCRF is simultaneously governed by margins, cross-correlated coefficients and copulas. The proper selection of these crucial factors can considerably reduce multi-source uncertainties. Overall, the proposed method could provide a useful guideline for accurately modeling cross-correlation random fields of soil slope.