Within-event spatial correlation of peak ground acceleration and spectral pseudo-acceleration ordinates in the Chilean subduction zone

A regional seismic risk assessment requires the estimation of ground-motion intensities at multiple locations for a given event simultaneously. In this context, the spatial correlation of ground-motion residuals plays an important role in characterizing the probability distribution of the field of shaking intensities. Over the last 20 years, the spatial correlation of ground-motions has been widely studied and different models have been developed. In general, these models vary from each other depending on the ground-motion database used to generate them, on the adopted intensity measure, on the selected ground-motion model, and on the estimation methods, among others. This paper proposes a spatial correlation model for within-event residuals of peak ground acceleration and spectral pseudo-acceleration ordinates in the Chilean subduction zone. Although the database considered for this study has only a few well-recorded earthquakes, it contains a large number of station pairs sharing several common events. Therefore, we compute non-stationary correlations between station pairs and then fit a stationary spatial correlation model. Results of this paper are compared with previous models, concluding that, in general, subduction models show higher spatial correlations than those for active shallow crust events for long-period spectral ordinates. Moreover, no evidence was found for a systematic effect of earthquake magnitude or site conditions on spatial correlation. Finally, the proposed model is compared with a model obtained assuming stationarity in spatial correlations, showing more reliable estimates when using the proposed model.