Proposal of an empirical site classification method based on target simulated horizontal over vertical spectral ratio

Abstract

Nowadays, most of the site classifications schemes are based on the predominant period of the site as determined from the average horizontal to vertical spectral ratios of seismic motion or microtremor. However, the difficulty lies in the identification of the predominant period in particular if the observed average response spectral ratio does not present a clear peak but rather a broadband amplification or multiple peaks. In this work, based on the Eurocode-8 (2004) site classification, and assuming bounded random fields for both shear and compression waves-velocities, damping coefficient, natural period and depth of soil profile, one propose a new site-classification approach, based on “target” simulated average $$ H/V $$ spectral ratios, defined for each soil class. Taking advantage of the relationship of Kawase et al. (Bull Seismol Soc Am 101:2001–2014, 2011), which link the $$ H/V $$ spectral ratio to the horizontal ( $$ HTF $$ ) over the vertical ( $$ VTF $$ ) transfer functions, statistics of $$ H/V $$ spectral ratio via deterministic visco-elastic seismic analysis using the wave propagation theory are computed for the 4 soil classes. The obtained results show that $$ H/V $$ and $$ HTF $$ have amplitudes and shapes remarkably different among the four soil classes and exhibit fundamental peaks in the period ranges remarkably similar. Moreover, the “target” simulated average $$ H/V $$ spectral ratios for the 4 soil classes are in good agreement with the experimental ones obtained by Zhao et al. (Bull Seismol Soc Am 96:914–925, 2006) from the abundant and reliable Japanese strong motions database Kik-net, Ghasemi et al. (Soil Dyn Earthq Eng 29:121–132, 2009) from the Iranian strong motion data, and Di Alessandro et al. (Bull Sesismol Soc Am 106:2, 2011. https://doi.org/10.1785/0120110084 ) from the Italian strong motion data. In addition to the 4 EC-8 standard soil classes (A, B, C and D), the superposition of the 4 target $$ H/V $$ reveals 3 new boundary site classes; AB, BC and CD, for overlapping $$ V_{s,30} $$ ranges when the predominant peak is not clearly consistent with any of the 4 proposed classes. Finally, one proposes a site classification index based on the ratio between the cross-correlation and the mean quadratic error between the in situ $$ H/V $$ spectral ratio and the “target” one. In order to test the reliability of the proposed approach, data from 139 sites were used, 132 collected from the Kik-net network database from Japan and 7 from Algeria. The site classification success rate per site class are around 93, 82, 89 and 100% for rock, hard soil, medium soil and soft soil, respectively. Zhao et al. (2006) found an average success for the 4 classes of soil close to 60%, similar to what one found in the present study (63%) without considering the new soil classes, but much smaller if one considers them (86%). In the absence of $$ V_{s,30} $$ data, the proposed approach can be an alternative to site classification.