A novel reliability method for assessing dam slope stability by incorporating intrinsic correlations of rockfill materials

Recently, slope reliability analysis based on probabilistic theory has advanced, most of which treat material properties solely as independent variables. However, the physical and mechanical parameters of rockfill are highly interrelated, ignoring these correlations can yield in inaccurate assessments of slope stability. Therefore, a novel method incorporating intrinsic correlation between material parameters for slope reliability analysis is proposed. Initially, the statistical characteristics of 36 rockfill dams in China are analyzed to determine the best marginal distribution for each Duncan-Chang E-B model parameter using the Akaike Information Criterion. The Kendall rank correlation coefficient is then used to reveal the relationships between the parameters, based on which a multidimensional joint probability model can be established by vine copula. Finally, the surrogate model of the performance function is developed, facilitating the slope reliability analysis that incorporates intrinsic correlations. The method is applied to the DL high rockfill dam, and results indicate that neglecting intrinsic correlations increases the slope failure probability and reduces the dam slope stability, resulting in overly conservative designs. In contrast, considering interrelationships provides a more accurate representation of practical scenarios and avoids the parameter distortion.