Transfer learning for low frequency extrapolation from shot gathers for FWI applications
Name:
transfer_ovcharenko_et_al_2019.pdf
Size:
1.091Mb
Format:
PDF
Description:
Accepted manuscript
Type
Conference PaperKAUST Department
Earth Science and Engineering ProgramExtreme Computing Research Center
Physical Science and Engineering (PSE) Division
Seismic Wave Analysis Group
Date
2019-08-26Permanent link to this record
http://hdl.handle.net/10754/661870
Metadata
Show full item recordAbstract
Low-frequency data proved to be crucial for robust full-waveform inversion (FWI) applications. However, acquiring those data in the field is a challenging and costly task. Deep neural networks can be trained to extrapolate missing low frequencies, but no optimal network configuration exists. Therefore, the search for an acceptable network architecture is a tedious empirical task whose outcome heavily affects the performance of the application. Here, we propose and utilize transfer learning to reduce the computational efforts otherwise spent on an optimal architecture search and an initial network training. We re-train the light-weight MobileNet convolutional network to infer low-frequency data from a frequency-domain representation of the individual shot-gathers, which leads to an efficient, yet accurate inference of low frequencies according to wavenumber theory. In particular, we show that the extrapolated 0.25 - 1 Hz from 2-4.5 Hz data are accurate enough for acoustic FWI on part of the original BP 2004 model and the Marmousi II model of double scale. We bridge the gap between the 1 Hz predicted and the 2 Hz modeled data by the application of a Sobolev space norm regularization.Citation
Ovcharenko, O., Kazei, V., Peter, D., & Alkhalifah, T. (2019). Transfer Learning For Low Frequency Extrapolation From Shot Gathers For FWI Applications. 81st EAGE Conference and Exhibition 2019. doi:10.3997/2214-4609.201901617Publisher
EAGE Publications BVConference/Event name
81st EAGE Conference and Exhibition 2019ae974a485f413a2113503eed53cd6c53
10.3997/2214-4609.201901617