TY - GEN
T1 - DL-fused elastic FWI: Application to marine streamer data
AU - Plotnitskii, Pavel
AU - Ovcharenko, Oleg
AU - Kazei, Vladimir
AU - Peter, Daniel
AU - Alkhalifah, Tariq Ali
N1 - KAUST Repository Item: Exported on 2022-09-14
PY - 2022/8/15
Y1 - 2022/8/15
N2 - 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.
AB - 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.
UR - http://hdl.handle.net/10754/680558
UR - https://library.seg.org/doi/10.1190/image2022-3745846.1
U2 - 10.1190/image2022-3745846.1
DO - 10.1190/image2022-3745846.1
M3 - Conference contribution
BT - Second International Meeting for Applied Geoscience & Energy
PB - Society of Exploration Geophysicists and American Association of Petroleum Geologists
ER -
