Deep Learning-based extraction of surface wave dispersion curves from seismic shot gathers

Abstract: Multi-channel Analysis of Surface Waves (MASW) is a seismic method employed to obtain useful information about shear-wave velocities in the near surface. A fundamental step in this methodology is the extraction of dispersion curves from dispersion spectra, which are obtained after applying specific processing algorithms onto the recorded shot gathers. Whilst this extraction process can be automated to some extent, it usually requires extensive quality control, which can be arduous for large datasets. We present a novel approach that leverages deep learning to identify a direct mapping between seismic shot gathers and their associated dispersion curves (for both fundamental and first modes), by-passing therefore the need to compute dispersion spectra. Given a site of interest, a set of 1D velocity and density models are created using prior knowledge of the local geology; pairs of seismic shot gathers and Rayleigh-wave phase dispersion curves are then numerically modeled and used to train a simplified residual network. The proposed approach is shown to achieve high quality predictions of dispersion curves on a synthetic test dataset and is, ultimately, successfully deployed on a field dataset. Various uncertainty quantification and CNN visualization techniques are also developed to assess the quality of the inference process and better understand the underlying learning process of the network. The predicted dispersion curves are finally inverted, and the resulting shear-wave velocity model is shown to be plausible and consistent with prior geological knowledge of the area.