Research output: Contribution to journal › Conference article › peer-review
Direct estimation of local wavefront attributes using deep learning. / Gadylshin, Kirill; Silvestrov, Ilya; Bakulin, Andrey.
In: SEG Technical Program Expanded Abstracts, Vol. 2021-September, 2021, p. 1596-1600.Research output: Contribution to journal › Conference article › peer-review
}
TY - JOUR
T1 - Direct estimation of local wavefront attributes using deep learning
AU - Gadylshin, Kirill
AU - Silvestrov, Ilya
AU - Bakulin, Andrey
N1 - Publisher Copyright: © 2021 Society of Exploration Geophysicists First International Meeting for Applied Geoscience & Energy
PY - 2021
Y1 - 2021
N2 - Wavefront attributes, such as local dips and curvatures of seismic events, are used in different seismic data processing methods, from prestack data enhancement to migration to tomography. The attributes' estimation for prestack data is a time-consuming and computationally expensive process. We propose a new approach based on U-Net convolutional neural network that directly map prestack seismic data to the local wavefront attributes. Using a 3D real data example, we demonstrate that this deep-learning-based approach can reduce the computational time by two orders of magnitude compared to a classical coherency-based optimization technique while preserving a reasonable quality of results.
AB - Wavefront attributes, such as local dips and curvatures of seismic events, are used in different seismic data processing methods, from prestack data enhancement to migration to tomography. The attributes' estimation for prestack data is a time-consuming and computationally expensive process. We propose a new approach based on U-Net convolutional neural network that directly map prestack seismic data to the local wavefront attributes. Using a 3D real data example, we demonstrate that this deep-learning-based approach can reduce the computational time by two orders of magnitude compared to a classical coherency-based optimization technique while preserving a reasonable quality of results.
UR - http://www.scopus.com/inward/record.url?scp=85120938014&partnerID=8YFLogxK
U2 - 10.1190/segam2021-3583265.1
DO - 10.1190/segam2021-3583265.1
M3 - Conference article
AN - SCOPUS:85120938014
VL - 2021-September
SP - 1596
EP - 1600
JO - SEG Technical Program Expanded Abstracts
JF - SEG Technical Program Expanded Abstracts
SN - 1052-3812
T2 - 1st International Meeting for Applied Geoscience and Energy
Y2 - 26 September 2021 through 1 October 2021
ER -
ID: 34969497