Oleg Ovcharenko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Oleg Ovcharenko has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Vladimir Kazei
Aramco Americas, Houston Research Center, Houston, Texas, USA.
10 shared publications - Daniel Peter
Seismic Modeling and Inversion Group, King Abdullah University of Science and Technology, 23955 Thuwal, Saudi Arabia
9 shared publications - Tariq Alkhalifah
Division of Physical Science and Engineering King Abdullah University of Science and Technology 23955-6900 Thuwal Saudi Arabia
5 shared publications T. Alkhalifah
4 shared publications- Pavel Plotnitskii
King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
2 shared publications C. Cuvilliez
1 shared publication
Latest Publications
- Open Access
- 1 December 2022
- Published by KEAI Publishing in Artificial Intelligence in Geosciences
- Vol. 3, 101-114
MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning
- 1 December 2022
- Published by KEAI Publishing in Artificial Intelligence in Geosciences
- Vol. 3, 101-114
Open AccessMLReal: Bridging the gap between training on synthetic data and real data applications in machine learning
- Open Access
- 23 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
Multi-Task Learning for Low-Frequency Extrapolation and Elastic Model Building From Seismic Data
Low-frequency (LF) signal content in seismic data as well as a realistic initial model are key ingredients for robust and efficient full-waveform inversions (FWIs). However, acquiring LF data is challenging in practice for active seismic surveys. Data-driven solutions show promise to extrapolate LF data given a high-frequency counterpart. While being established for synthetic acoustic examples, the application of bandwidth extrapolation to field datasets remains nontrivial. Rather than aiming to reach superior accuracy in bandwidth extrapolation, we propose to jointly reconstruct LF data and a smooth background subsurface model within a multitask deep learning framework. We automatically balance data, model, and trace-wise correlation loss terms in the objective functional and show that this approach improves the extrapolation capability of the network. We also design a pipeline for generating synthetic data suitable for field data applications. Finally, we apply the same trained network to synthetic and real marine streamer datasets and run an elastic FWI from the extrapolated dataset.
- 23 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
Open AccessMulti-Task Learning for Low-Frequency Extrapolation and Elastic Model Building From Seismic Data
Low-frequency (LF) signal content in seismic data as well as a realistic initial model are key ingredients for robust and efficient full-waveform inversions (FWIs). However, acquiring LF data is challenging in practice for active seismic surveys. Data-driven solutions show promise to extrapolate LF data given a high-frequency counterpart. While being established for synthetic acoustic examples, the application of bandwidth extrapolation to field datasets remains nontrivial. Rather than aiming to reach superior accuracy in bandwidth extrapolation, we propose to jointly reconstruct LF data and a smooth background subsurface model within a multitask deep learning framework. We automatically balance data, model, and trace-wise correlation loss terms in the objective functional and show that this approach improves the extrapolation capability of the network. We also design a pipeline for generating synthetic data suitable for field data applications. Finally, we apply the same trained network to synthetic and real marine streamer datasets and run an elastic FWI from the extrapolated dataset.
- Open Access
- 31 August 2021
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 86 (5) , R711-R721
Mapping full seismic waveforms to vertical velocity profiles by deep learning
Building realistic and reliable models of the subsurface is the primary goal of seismic imaging. We have constructed an ensemble of convolutional neural networks (CNNs) to build velocity models directly from the data. Most other approaches attempt to map full data into 2D labels. We exploit the regularity of seismic acquisition and train CNNs to map gathers of neighboring common midpoints (CMPs) to vertical 1D velocity logs. This allows us to integrate well-log data into the inversion, simplify the mapping by using the 1D labels, and accommodate larger dips relative to using single CMP inputs. We dynamically generate the training data in parallel with training the CNNs, which reduces overfitting. Data generation and training of CNNs is more computationally expensive than conventional full-waveform inversion (FWI). However, once the network is trained, data sets with similar acquisition parameters can be inverted much faster than with FWI. The multiCMP CNN ensemble is tested on multiple realistic synthetic models, performs well, and was combined with FWI for even better performance.
- 31 August 2021
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 86 (5) , R711-R721
Open AccessMapping full seismic waveforms to vertical velocity profiles by deep learning
Building realistic and reliable models of the subsurface is the primary goal of seismic imaging. We have constructed an ensemble of convolutional neural networks (CNNs) to build velocity models directly from the data. Most other approaches attempt to map full data into 2D labels. We exploit the regularity of seismic acquisition and train CNNs to map gathers of neighboring common midpoints (CMPs) to vertical 1D velocity logs. This allows us to integrate well-log data into the inversion, simplify the mapping by using the 1D labels, and accommodate larger dips relative to using single CMP inputs. We dynamically generate the training data in parallel with training the CNNs, which reduces overfitting. Data generation and training of CNNs is more computationally expensive than conventional full-waveform inversion (FWI). However, once the network is trained, data sets with similar acquisition parameters can be inverted much faster than with FWI. The multiCMP CNN ensemble is tested on multiple realistic synthetic models, performs well, and was combined with FWI for even better performance.
- 1 January 2020
- Published by EAGE Publications bv
- Vol. 2020 (1) , 1-5
Extrapolation of Low Wavenumbers in FWI Gradients by a Deep Convolutional Neural Network
- 1 January 2020
- Published by EAGE Publications bv
- Vol. 2020 (1) , 1-5
Extrapolation of Low Wavenumbers in FWI Gradients by a Deep Convolutional Neural Network
- Open Access
- 11 November 2019
- Published by Taylor & Francis in ASEG Extended Abstracts
- Vol. 2019 (1) , 1-5
Seismic model low wavenumber extrapolation by a deep convolutional neural network
Conventional seismic data are naturally mainly sensitive to the very smooth velocity variations that alter transmission traveltimes (low-model wavenumbers) and very abrupt discontinuities that cause reflections (high-model wavenumbers). Full-waveform inversion (FWI) of seismic data inherits this lack of middle model wavenumber illumination, which results into ringy artifacts in the gradients. Multiple methods have been suggested to overcome this issue. Here we tackle the problem of missing wavenumbers with a deep-learning approach. Namely, we filter out the wavenumbers that are expected to be missing from the acquisition design and then train a deep convolutional neural network to provide the missing wavenumbers trace-by-trace. We test several network configurations and several training sets derived from the Marmousi II model. The neural network shows limited capabilities in generalizing from the input data sets. We also report a tradeoff between the generalization abilities and accuracy on the training data set.
- 11 November 2019
- Published by Taylor & Francis in ASEG Extended Abstracts
- Vol. 2019 (1) , 1-5
Open AccessSeismic model low wavenumber extrapolation by a deep convolutional neural network
Conventional seismic data are naturally mainly sensitive to the very smooth velocity variations that alter transmission traveltimes (low-model wavenumbers) and very abrupt discontinuities that cause reflections (high-model wavenumbers). Full-waveform inversion (FWI) of seismic data inherits this lack of middle model wavenumber illumination, which results into ringy artifacts in the gradients. Multiple methods have been suggested to overcome this issue. Here we tackle the problem of missing wavenumbers with a deep-learning approach. Namely, we filter out the wavenumbers that are expected to be missing from the acquisition design and then train a deep convolutional neural network to provide the missing wavenumbers trace-by-trace. We test several network configurations and several training sets derived from the Marmousi II model. The neural network shows limited capabilities in generalizing from the input data sets. We also report a tradeoff between the generalization abilities and accuracy on the training data set.
- Top Cited Papers
- 30 October 2019
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 84 (6) , R989-R1001
Deep learning for low-frequency extrapolation from multioffset seismic data
Low-frequency seismic data are crucial for convergence of full-waveform inversion (FWI) to reliable subsurface properties. However, it is challenging to acquire field data with an appropriate signal-to-noise ratio in the low-frequency part of the spectrum. We have extrapolated low-frequency data from the respective higher frequency components of the seismic wavefield by using deep learning. Through wavenumber analysis, we find that extrapolation per shot gather has broader applicability than per-trace extrapolation. We numerically simulate marine seismic surveys for random subsurface models and train a deep convolutional neural network to derive a mapping between high and low frequencies. The trained network is then tested on sections from the BP and SEAM Phase I benchmark models. Our results indicate that we are able to recover 0.25 Hz data from the 2 to 4.5 Hz frequencies. We also determine that the extrapolated data are accurate enough for FWI application.
- 30 October 2019
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 84 (6) , R989-R1001
Top Cited PapersDeep learning for low-frequency extrapolation from multioffset seismic data
Low-frequency seismic data are crucial for convergence of full-waveform inversion (FWI) to reliable subsurface properties. However, it is challenging to acquire field data with an appropriate signal-to-noise ratio in the low-frequency part of the spectrum. We have extrapolated low-frequency data from the respective higher frequency components of the seismic wavefield by using deep learning. Through wavenumber analysis, we find that extrapolation per shot gather has broader applicability than per-trace extrapolation. We numerically simulate marine seismic surveys for random subsurface models and train a deep convolutional neural network to derive a mapping between high and low frequencies. The trained network is then tested on sections from the BP and SEAM Phase I benchmark models. Our results indicate that we are able to recover 0.25 Hz data from the 2 to 4.5 Hz frequencies. We also determine that the extrapolated data are accurate enough for FWI application.
- 1 January 2019
- Published by EAGE Publications bv
Realistically Textured Random Velocity Models for Deep Learning Applications
- 1 January 2019
- Published by EAGE Publications bv
Realistically Textured Random Velocity Models for Deep Learning Applications
- 1 January 2019
- Published by EAGE Publications bv
- p. 1-5
Transfer Learning For Low Frequency Extrapolation From Shot Gathers For FWI Applications
- 1 January 2019
- Published by EAGE Publications bv
- p. 1-5
Transfer Learning For Low Frequency Extrapolation From Shot Gathers For FWI Applications
- 1 September 2018
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 83 (5) , R541-R551
Variance-based model interpolation for improved full-waveform inversion in the presence of salt bodies
When present in the subsurface, salt bodies impact the complexity of wave-equation-based seismic imaging techniques, such as least-squares reverse time migration and full-waveform inversion (FWI). Typically, the Born approximation used in every iteration of least-squares-based inversions is incapable of handling the sharp, high-contrast boundaries of salt bodies. We have developed a variance-based method for reconstruction of velocity models to resolve the imaging and inversion issues caused by salt bodies. Our main idea lies in retrieving useful information from independent updates corresponding to FWI at different frequencies. After several FWI iterations, we compare the model updates by considering the variance distribution between them to identify locations most prone to cycle skipping. We interpolate velocities from the surrounding environment into these high-variance areas. This approach allows the model to gradually improve from identifying easily resolvable areas and extrapolating the model updates from those to the areas that are difficult to resolve at early FWI iterations. In numerical tests, our method demonstrates the ability to obtain convergent FWI results at higher frequencies.
- 1 September 2018
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 83 (5) , R541-R551
Variance-based model interpolation for improved full-waveform inversion in the presence of salt bodies
When present in the subsurface, salt bodies impact the complexity of wave-equation-based seismic imaging techniques, such as least-squares reverse time migration and full-waveform inversion (FWI). Typically, the Born approximation used in every iteration of least-squares-based inversions is incapable of handling the sharp, high-contrast boundaries of salt bodies. We have developed a variance-based method for reconstruction of velocity models to resolve the imaging and inversion issues caused by salt bodies. Our main idea lies in retrieving useful information from independent updates corresponding to FWI at different frequencies. After several FWI iterations, we compare the model updates by considering the variance distribution between them to identify locations most prone to cycle skipping. We interpolate velocities from the surrounding environment into these high-variance areas. This approach allows the model to gradually improve from identifying easily resolvable areas and extrapolating the model updates from those to the areas that are difficult to resolve at early FWI iterations. In numerical tests, our method demonstrates the ability to obtain convergent FWI results at higher frequencies.
- 11 June 2018
- Published by EAGE Publications bv
Low-Frequency Data Extrapolation Using a Feed-Forward ANN
- 11 June 2018
- Published by EAGE Publications bv
Low-Frequency Data Extrapolation Using a Feed-Forward ANN