Synthetic inversions for density using seismic and gravity data

Density variations drive mass transport in the Earth from plate tectonics to convection in the mantle and core. Nevertheless, density remains poorly known because most geophysical measurements used to probe the Earth's interior either have little sensitivity to density, suffer from trade-offs or from non-uniqueness. With the ongoing expansion of computational power, it has become possible to accurately model complete seismic wavefields in a 3-D heterogeneous Earth, and to develop waveform inversion techniques that account for complicated wavefield effects. This may help to improve resolution of density. Here, we present a pilot study where we explore the extent to which waveform inversion may be used to better recover density as a separate, independent parameter. We perform numerical simulations in 2-D to investigate under which conditions, and to what extent density anomalies may be recovered in the Earth's mantle. We conclude that density can indeed be constrained by seismic waveforms, mainly as a result of scattering effects at density contrasts. As a consequence, the low-frequency part of the wavefield is the most important for constraining the actual extent of anomalies. While the impact of density heterogeneities on the wavefield is small compared to the effects of velocity variations, it is likely to be detectable in modern regional-to global-scale measurements. We also conclude that the use of gravity data as additional information does not help to further improve the recovery of density anomalies unless strong a priori constraints on the geometry of density variations are applied. This is a result of the inherent physical non-uniqueness of potential-field inverse problems. Finally, in the limited numerical setup that we employ, we find that the initially supplied anomalies in S- and P-velocity models are of minor importance.