Результаты исследований: Материалы конференций › материалы › Рецензирование
Inpainting of local wavefront attributes using artificial intelligence. / Gadylshin, Kirill; Silvestrov, Ilya; Bakulin, Andrey.
2020. 2212-2216 Работа представлена на Society of Exploration Geophysicists International Exposition and Annual Meeting 2019, SEG 2019, San Antonio, Соединенные Штаты Америки.Результаты исследований: Материалы конференций › материалы › Рецензирование
}
TY - CONF
T1 - Inpainting of local wavefront attributes using artificial intelligence
AU - Gadylshin, Kirill
AU - Silvestrov, Ilya
AU - Bakulin, Andrey
N1 - Funding Information: The authors would like to thank Maxim Dmitriev (Saudi Aramco) for support of the field study. One of the authors (Kirill Gadylshin) was partially supported by RFBR grant no. 18-35-00253 and the Russian Government Grant MK-670.2019.5. Publisher Copyright: © 2019 SEG Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020
Y1 - 2020
N2 - We propose a fast method to calculate local wavefront attributes for 3D prestack seismic data. First step is to compute attributes on a coarse regular or irregular grid in time and space using conventional approaches. Second step is very fast and efficient inpainting of the attributes in remaining locations by artificial intelligence utilizing a specially trained deep neural network. The method incorporates multi-parameter attributes using a special colouring scheme and allows estimation of multiple attributes simultaneously during one run. We demonstrate that inpainting of local wavefront attributes for nonlinear beamforming can greatly speed up prestack enhancement of 3D seismic data. Other applications such as velocity analysis or seismic tomography can be implemented using a similar approach.
AB - We propose a fast method to calculate local wavefront attributes for 3D prestack seismic data. First step is to compute attributes on a coarse regular or irregular grid in time and space using conventional approaches. Second step is very fast and efficient inpainting of the attributes in remaining locations by artificial intelligence utilizing a specially trained deep neural network. The method incorporates multi-parameter attributes using a special colouring scheme and allows estimation of multiple attributes simultaneously during one run. We demonstrate that inpainting of local wavefront attributes for nonlinear beamforming can greatly speed up prestack enhancement of 3D seismic data. Other applications such as velocity analysis or seismic tomography can be implemented using a similar approach.
UR - http://www.scopus.com/inward/record.url?scp=85079507578&partnerID=8YFLogxK
U2 - 10.1190/segam2019-3214642.1
DO - 10.1190/segam2019-3214642.1
M3 - Paper
AN - SCOPUS:85079507578
SP - 2212
EP - 2216
T2 - Society of Exploration Geophysicists International Exposition and Annual Meeting 2019, SEG 2019
Y2 - 15 September 2019 through 20 September 2019
ER -
ID: 27734405