Trans-dimensional imaging of the random inhomogeneity structure in the southern Ryukyu arc, Japan

Abstract

SUMMARY The seismic velocity structure of the lithosphere shows various inhomogeneities over a wide range of scales, and such inhomogeneity causes complex seismic waves above a few hertz due to multiple scattering. Medium around active volcanoes and large faults tends to show strong random inhomogeneity in relatively small areas. For a more precise understanding of such random velocity inhomogeneities, it is necessary to estimate their detailed spatial variation without smoothing constraints. This study introduces a trans-dimensional approach for the 3-D imaging of random inhomogeneity using the reversible jump Markov chain Monte Carlo (rjMCMC) method, and set the number of structural parameters and their spatial layout as unknown parameters. Since the scale dependence of the random inhomogeneity is related to the frequency dependence of seismic wave scattering, the covariance matrix of the likelihood function was defined to be non-diagonal so that residuals at different frequencies in each ray path are correlated. A synthetic test showed this covariance matrix worked adequately for estimating parameters of a power-law-type spectrum of random inhomogeneity. Analysis of seismic data at the southern Ryukyu arc in the southwest Japan found anomalies with strong and weak inhomogeneities. A strongly inhomogeneous band with a width of 20–30 km was distributed in the Okinawa Trough at depths of 0–20 km. In part of this area, magma intrusions and associated complex structures have been detected by a seismic reflection survey. The scale of the structures discussed in this study is almost the same with that discussed in the reflection survey. The rjMCMC-based analysis made it possible to compare random inhomogeneities with the structural variations estimated by the deterministic seismic reflection survey. Since analyses of scattered seismic waves can examine much greater depths than seismic reflection surveys, further comparisons between the two methods in the shallow crust could provide useful insights for detailed interpretation of complex structures at deeper depth.