Low-frequency data is crucial for successful retrieval of low-wavenumber model component in seismic full-waveform inversion (FWI), yet it is often limited by hardware. Deep learning (DL) can fuse early high-wavenumber updates of elastic FWI and map them into desired low-wavenumber updates that would be available from low-frequency data. FusionNET-based convolutional neural network (CNN) trained on a synthetic dataset produces meaningful low-wavenumber models taking initial FWI iterations on field data as inputs. Elastic FWI initiated from ”DL-fused” model updates shows improved convergence on synthetic data generated in unrelated to training dataset models and on real-world marine streamer data.
|Original language||English (US)|
|Title of host publication||Second International Meeting for Applied Geoscience & Energy|
|Publisher||Society of Exploration Geophysicists and American Association of Petroleum Geologists|
|State||Published - Aug 15 2022|