Jinsong Huang

TL;DR: In this article, the authors investigated the probability of failure of slopes using both traditional and more advanced probabilistic analysis tools, and they showed that simplified analysis in which spatial variability of soil properties is not properly accounted for, can lead to unconservative estimates of the failure probability if the coefficient of variation of the shear strength parameters exceeds a critical value.

TL;DR: The asymmetric and unsupervised FC-SAE can extract optimal non-linear features from environmental factors successfully, outperforms some conventional machine learning methods, and is promising for LSP.

TL;DR: In this article, the authors describe a methodology in which parameters such as the soil strength, slope geometry and pore pressures, are generated using random field theory, and demonstrate the important "seeking out" effect of failure mechanisms in spatially random materials, and how first order methods that may not properly account for spatial variability can lead to unconservative estimates of the probability of slope failure.

TL;DR: A multivariate chaotic ELM model is proposed for the prediction of the displacement of reservoir landslides in China and it is shown that the model achieves higher prediction accuracy than the univariate chaoticELM model and the multivariate chaos PSO-SVM model.

TL;DR: In this article, a new framework of quantitative landslide risk assessment, in which consequences are assessed individually, is proposed, which is generally applicable, and the landslide risk assessments of two typical slopes are presented.