Comment on 'Banana-doughnut kernels and mantle tomography' by van der Hilst and de Hoop

The claim by van der Hilst and de Hoop that finite-frequency (FF) inversion of seismic traveltimes does not result in measurable improvements in tomographic images is misguided, and based upon a biased selection of images in the upper mantle, where wave front healing effects are indeed small, and where our models are generally poorly resolved because we primarily used teleseismic waves that travel steeply in the upper mantle; and upon an improper application of statistics to the better-resolved anomalies in the lower mantle. If station corrections for long-period P waves are computed using ray theory, as we do, unmodelled FF effects may be responsible for slow anomalies of up to 0.3 per cent beneath very small island stations, but these effects are negligible for larger islands such as Reunion and Kerguelen. The presence of a plume beneath these islands is the most probable explanation for the observed low velocities.