Physics-based parametrization of a FAS nonergodic ground motion model for Central Italy

We propose a new fully nonergodic ground motion model for Central Italy, which is one of the most sampled areas in the world after the occurrence of the last seismic sequences of 2009 and 2016-2017. The model predicts 69 ordinates of the Fourier Amplitude Spectrum in the magnitude range 3.2-6.5 and is constrained on a dense set of seismological and geophysical parameters (i.e. stress-drop ?s , shear-wave velocity in the uppermost 30 m, V-S,V-30 and high-frequency attenuation parameter at source ?(source) and site ?(0)) made available from a non-parametric generalized inversion technique (GIT). The aim of this work is to capture the underlying physics of ground motion related to different source energy levels, as well as to the crustal and geological structure of the region, thus providing less uncertain predictions. Calibration is performed using a stepwise regression approach which has the advantage of taking a more complex functional form (advanced model) when all physical parameters are known while returning a simpler form (base model) when physical data are missing. As a result, the advanced model reproduces the reference rock motion of the region in case the site additional proxies are set to their average values (V-S,V-30 = 1100 m/s, ?(0) =15 ms). We show that the inclusion of the set of physically-based explanatory variables in the regression has a beneficial effect in constraining the uncertainty, leading to a reduction of the high-frequency variability of about 70% on the between-event and 35% on the site to-site. This reduction can be viewed as the result of the combination of a more effective physical description through the incorporation of the additional proxies and a calibration embedded in a completely nonergodic framework.