A ground motion prediction model for the Italian region based on a mixture of experts framework

Abstract. Earthquake ground-motion prediction is crucial for seismic design, seismic hazard assessment, and the resilience of urban infrastructure. Although extensive research has been conducted for Italy, existing models cover only a limited range of earthquake types, exhibit insufficient accuracy and uncertainty control under complex scenarios – thus lowering reliability – and provide a restricted set of ground-motion intensity measures (IMs) that cannot meet the multi-indicator needs of engineering practice and risk assessment. To address these issues, this study proposes a ground-motion prediction model for Italy based on a Mixture of experts (MOE) framework, in which XGBoost is employed as the expert submodels to enhance predictive accuracy and stability across diverse scenarios. We conduct a systematic comparison between the proposed MOE-XGB and a baseline Gaussian process regression model with an exponential kernel (GPR, exponential). The results show stable and balanced improvements across multiple IMs – such as peak ground acceleration (PGA), peak ground velocity (PGV), and spectral acceleration (SA) at different periods – demonstrating advantages in both accuracy and robustness. Furthermore, using the larger and more diverse ITACA (Italian Accelerometric Archive) dataset, we retrain and evaluate MOE-XGB. The model achieves higher accuracy on all considered metrics and maintains stable performance in generalization tests based on independent earthquake events, highlighting strong generalization capability and robustness. In summary, the proposed MOE-XGB provides a high-accuracy and broadly applicable solution for ground-motion prediction in Italy; meanwhile, the framework exhibits good transferability and scalability, offering a useful reference for fusion-model-driven ground-motion prediction in Europe and other regions.