TY - JOUR
T1 - High-resolution reservoir characterization using deep learning aided elastic full-waveform inversion: The North Sea field data example
AU - Zhang, Zhendong
AU - Alkhalifah, Tariq Ali
N1 - KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: We thank Jeffrey Shragge, Weichang Li, Wenyi Hu and two anonymous reviewers, for the effort put into the review of the manuscript. We also want to thank Equinor and the former Volve license partners ExxonMobil E&P Norway AS and Bayerngas Norge AS, for the release
of the Volve data. The views expressed in this paper are the views of the authors and do not necessarily reflect the views of Equinor and the former Volve field license partners. For computer time, this research used the resources of the Supercomputing Laboratory at King
Abdullah University of Science & Technology (KAUST) in Thuwal, Saudi Arabia.
PY - 2020/1/29
Y1 - 2020/1/29
N2 - Reservoir characterization is an essential component of oil and gas production, as well as exploration. Classic reservoir characterization algorithms, both deterministic and stochastic, are typically based on stacked images and rely on simplifications and approximations to the subsurface (e.g., assuming linearized reflection coefficients). Elastic full-waveform inversion, which aims to match the waveforms of pre-stack seismic data, potentially provide more accurate high-resolution reservoir characterization from seismic data. However, full-waveform inversion can easily fail to characterize deep-buried reservoirs due to illumination limitations. We present a deep learning aided elastic full-waveform inversion strategy using observed seismic data and available well logs in the target area. Five facies are extracted from the well and then connected to the inverted P- and S-wave velocities using trained neural networks, which correspond to the subsurface facies distribution. Such a distribution is further converted to the desired reservoir-related parameters such as velocities and anisotropy parameters using a weighted summation. Finally, we update these estimated parameters by matching the resulting simulated wavefields to the observed seismic data, which corresponds to another round of elastic full-waveform inversion aided by the a priori knowledge gained from the predictions of machine learning. A North Sea field data example, the Volve Oil Field data set, indicates that the use of facies as prior helps resolve the deep-buried reservoir target better than the use of only seismic data.
AB - Reservoir characterization is an essential component of oil and gas production, as well as exploration. Classic reservoir characterization algorithms, both deterministic and stochastic, are typically based on stacked images and rely on simplifications and approximations to the subsurface (e.g., assuming linearized reflection coefficients). Elastic full-waveform inversion, which aims to match the waveforms of pre-stack seismic data, potentially provide more accurate high-resolution reservoir characterization from seismic data. However, full-waveform inversion can easily fail to characterize deep-buried reservoirs due to illumination limitations. We present a deep learning aided elastic full-waveform inversion strategy using observed seismic data and available well logs in the target area. Five facies are extracted from the well and then connected to the inverted P- and S-wave velocities using trained neural networks, which correspond to the subsurface facies distribution. Such a distribution is further converted to the desired reservoir-related parameters such as velocities and anisotropy parameters using a weighted summation. Finally, we update these estimated parameters by matching the resulting simulated wavefields to the observed seismic data, which corresponds to another round of elastic full-waveform inversion aided by the a priori knowledge gained from the predictions of machine learning. A North Sea field data example, the Volve Oil Field data set, indicates that the use of facies as prior helps resolve the deep-buried reservoir target better than the use of only seismic data.
UR - http://hdl.handle.net/10754/661506
UR - https://library.seg.org/doi/10.1190/geo2019-0340.1
U2 - 10.1190/geo2019-0340.1
DO - 10.1190/geo2019-0340.1
M3 - Article
SN - 0016-8033
SP - 1
EP - 47
JO - GEOPHYSICS
JF - GEOPHYSICS
ER -