Intelligent Assessment of Landslide Impact Force Considering the Uncertainty of Strength Parameters

Accurately predicting the peak impact force exerted by landslides on bridge piers is crucial for evaluating structural safety. However, the reliability of such predictions is frequently undermined by the spatial variability and uncertainty inherent in soil and rock strength parameters. To quantify the influence of this uncertainty, in this study, a three-dimensional numerical model of a landslide impacting bridge piers was developed using LS-DYNA software (version R11.0.0). A neural network was then trained on the peak impact forces simulated by the numerical model. Based on the neural network predictions, the impact mechanisms were categorized into two distinct modes, namely, a low-impact mode and a high-impact mode, for a comparative analysis. The results revealed statistically significant differences in soil parameters between these modes. Specifically, low-impact forces (F < 467 kN) were found to correlate with higher cohesion (18.5–24.9 kPa) and lower internal friction angles (15–22.4°). Conversely, high-impact forces (F ≥ 467 kN) were associated with lower cohesion (14.0–21.6 kPa) and higher internal friction angles (18.1–25.3°). This negative correlation highlights the decisive role that the combined uncertainty of strength parameters plays in predicting the peak impact force. Moreover, the surrogate model developed in this study effectively addresses the computational inefficiencies commonly associated with Monte Carlo simulations. This methodology provides a valuable tool for evaluating the vulnerability of infrastructure systems exposed to landslide hazards.