• Corpus ID: 230437497

Deep learning for low frequency extrapolation of multicomponent data in elastic full waveform inversion

  title={Deep learning for low frequency extrapolation of multicomponent data in elastic full waveform inversion},
  author={Hongyu Sun and Laurent Demanet},
Full waveform inversion (FWI) strongly depends on an accurate starting model to succeed. This is particularly true in the elastic regime: The cycle-skipping phenomenon is more severe in elastic FWI compared to acoustic FWI, due to the short S-wave wave-length. In this paper, we extend our work on extrapolated FWI (EFWI) by proposing to synthesize the low frequencies of multi-component elastic seismic records, and use those “artificial” low frequencies to seed the frequency sweep of elastic FWI… 


Extrapolated full-waveform inversion with deep learning
An architecture of convolutional neural network (CNN) is proposed to automatically extrapolate the missing low frequencies without preprocessing and post-processing steps to offer a tantalizing solution to the problem of properly initializing FWI.
Low-frequency extrapolation with deep learning
This paper proposes a deep-learning-based bandwidth extension method by considering low frequency extrapolation as a regression problem, and seems to offer a tantalizing solution to the problem of properly initializing FWI.
Deep learning for low-frequency extrapolation from multioffset seismic data
Low-frequency seismic data are crucial for convergence of full-waveform inversion (FWI) to reliable subsurface properties. However, it is challenging to acquire field data with an appropriate
Low-Frequency Data Extrapolation Using a Feed-Forward ANN
Full-waveform inversion (FWI) benefits in many ways from having low-frequency data. However, those are rarely available due to acquisition limitations. Here, we explore the feasibility of
Full Waveform Inversion With Extrapolated Low Frequency Data
This paper explores the possibility of synthesizing the low frequencies computationally from high-frequency data, and uses the resulting prediction of the missing data to seed the frequency sweep of FWI and demonstrates surprising robustness to the inaccuracies in the extrapolated low frequency data.
Progressive transfer learning for low frequency data prediction in full waveform inversion
The synthetic numerical experiments suggest that the LF data predicted by the progressive transfer learning are sufficiently accurate for an FWI engine to produce reliable subsurface velocity models free of cycle-skipping artifacts.
The importance of transfer learning in seismic modeling and imaging
Accurate forward modeling is essential for solving inverse problems in exploration seismology. Unfortunately, it is often not possible to afford being physically or numerically accurate. To overcome
Data-Driven Seismic Waveform Inversion: A Study on the Robustness and Generalization
This article developed a real-time data-driven technique and it is called VelocityGAN, to reconstruct accurately the subsurface velocities and develops a transfer-learning strategy based on VelocityGAN to alleviate the generalization issue.
Multiparameter waveform inversion of a large wide-azimuth low-frequency land data set in Oman
ABSTRACTSeveral 3D seismic acoustic full-waveform inversions (FWIs) of offshore data sets have been reported over the last five years. A successful updating of the long-to-intermediate wavelengths of
Deep-learning inversion: a next generation seismic velocity-model building method
A novel method based on the supervised deep fully convolutional neural network (FCN) for velocity-model building (VMB) directly from raw seismograms is investigated, showing promising performances in comparison with conventional FWI even when the input data are in more realistic scenarios.