Dual-band generative learning for low-frequency extrapolation in seismic land data
Type
Conference PaperAuthors
Ovcharenko, Oleg
Kazei, Vladimir
Peter, Daniel

Silvestrov, Ilya
Bakulin, Andrey
Alkhalifah, Tariq Ali

KAUST Department
Earth Science and Engineering ProgramExtreme Computing Research Center
Physical Science and Engineering (PSE) Division
Seismic Wave Analysis Group
Date
2021-09-01Online Publication Date
2021-09-01Print Publication Date
2021-09-01Permanent link to this record
http://hdl.handle.net/10754/670950
Metadata
Show full item recordAbstract
The presence of low-frequency energy in seismic data can help mitigate cycle-skipping problems in full-waveform inversion. Unfortunately, the generation and recording of low-frequency signals in seismic exploration remains a non-trivial task. Extrapolation of missing low-frequency content in field data might be addressed in a data-driven framework. In particular, deep learning models trained on synthetic data could be used for inference on the field data. Such an implementation of switching application domains remains challenging. We, therefore, propose the concept of generative dual-band learning to facilitate the knowledge transfer between synthetic and field seismic data applications of low-frequency data extrapolation. We first explain the two-step procedure for training a generative adversarial network (GAN) that extrapolates low frequencies. Then, we describe the workflow for synthetic dataset generation. Finally, we explore the feasibility of the dual-band learning concept on real near-surface land data acquired in Saudi Arabia. The presence of low-frequency energy in seismic data can help mitigate cycle-skipping problems in full-waveform inversion. Unfortunately, the generation and recording of low-frequency signals in seismic exploration remains a non-trivial task. Extrapolation of missing low-frequency content in field data might be addressed in a data-driven framework. In particular, deep learning models trained on synthetic data could be used for inference on the field data. Such an implementation of switching application domains remains challenging. We, therefore, propose the concept of generative dual-band learning to facilitate the knowledge transfer between synthetic and field seismic data applications of low-frequency data extrapolation. We first explain the two-step procedure for training a generative adversarial network (GAN) that extrapolates low frequencies. Then, we describe the workflow for synthetic dataset generation. Finally, we explore the feasibility of the dual-band learning concept on real near-surface land data acquired in Saudi Arabia.Citation
Ovcharenko, O., Kazei, V., Peter, D., Silvestrov, I., Bakulin, A., & Alkhalifah, T. (2021). Dual-band generative learning for low-frequency extrapolation in seismic land data. First International Meeting for Applied Geoscience & Energy Expanded Abstracts. doi:10.1190/segam2021-3579442.1Sponsors
The research reported in this publication was supported by funding from Saudi Aramco and King Abdullah University of Science and Technology (KAUST).Publisher
Society of Exploration GeophysicistsAdditional Links
https://library.seg.org/doi/10.1190/segam2021-3579442.1ae974a485f413a2113503eed53cd6c53
10.1190/segam2021-3579442.1