DispersioNET: Joint Inversion of Rayleigh-Wave Multimode Phase Velocity Dispersion Curves using Convolutional Neural Networks
This addresses a domain-specific problem in near-surface geophysics for researchers and practitioners, offering an incremental improvement by applying deep learning to an existing bottleneck.
The paper tackled the ill-posed and nonlinear inverse problem of inverting Rayleigh wave dispersion curves for shear wave velocity profiles by introducing DispersioNET, a CNN-based model for joint inversion of fundamental and higher order modes, which predicted S-wave velocity profiles closely matching true velocities in both noise-free and noisy datasets.
Rayleigh wave dispersion curves have been widely used in near-surface studies, and are primarily inverted for the shear wave (S-wave) velocity profiles. However, the inverse problem is ill-posed, non-unique and nonlinear. Here, we introduce DispersioNET, a deep learning model based on convolution neural networks (CNN) to perform the joint inversion of Rayleigh wave fundamental and higher order mode phase velocity dispersion curves. DispersioNET is trained and tested on both noise-free and noisy dispersion curve datasets and predicts S-wave velocity profiles that match closely with the true velocities. The architecture is agnostic to variations in S-wave velocity profiles such as increasing velocity with depth and intermediate low-velocity layers, while also ensuring that the output remains independent of the number of layers.