InversionNet3D: Efficient and Scalable Learning for 3-D Full-Waveform Inversion

Zeng, Qili; Feng, Shihang; Wohlberg, Brendt Egon; Lin, Youzuo

doi:10.1109/tgrs.2021.3135354

InversionNet3D: Efficient and Scalable Learning for 3-D Full-Waveform Inversion

Journal Article · Mon Dec 13 00:00:00 EST 2021 · IEEE Transactions on Geoscience and Remote Sensing

DOI:https://doi.org/10.1109/tgrs.2021.3135354· OSTI ID:1900478

^[1]; ^[1]; ^[1]; ^[1]

Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Seismic full-waveform inversion (FWI) techniques aim to find a high-resolution subsurface geophysical model provided with waveform data. Some recent effort in data-driven FWI has shown some encouraging results in obtaining 2-D velocity maps. However, due to high computational complexity and large memory consumption, the reconstruction of 3-D high-resolution velocity maps via deep networks is still a great challenge. Here, in this article, we present InversionNet3D (InvNet3D), an efficient and scalable encoder–decoder network for 3-D FWI. The proposed method employs group convolution in the encoder to establish an effective hierarchy for learning information from multiple sources while cutting down unnecessary parameters and operations at the same time. The introduction of invertible layers further reduces the memory consumption of intermediate features during training and, thus, enables the development of deeper networks with more layers and higher capacity as required by different application scenarios. Experiments on the 3-D Kimberlina dataset demonstrate that InvNet3D achieves state-of-the-art reconstruction performance with lower computational cost and lower memory footprint compared to the baseline.

View Accepted Manuscript (DOE)

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 1900478

Report Number(s):: LA-UR-21-22293

Journal Information:: IEEE Transactions on Geoscience and Remote Sensing, Journal Name: IEEE Transactions on Geoscience and Remote Sensing Vol. 60; ISSN 0196-2892

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (50)

A Sensitivity Study on Regional Pressure Buildup from Large-Scale CO2 Storage Projects Birkholzer, J. T.; Zhou, Q.; Cortis, A. Energy Procedia, Vol. 4 https://doi.org/10.1016/j.egypro.2011.02.389	journal	January 2011
Correction for Carcione, Energy balance and fundamental relations in dynamic anisotropic poro-viscoelasticity Carcione, J. M. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, Vol. 458, Issue 2028 https://doi.org/10.1098/rspa.2002.2000	journal	December 2002
Masked Autoregressive Flow for Density Estimation Papamakarios, George; Pavlakou, Theo; Murray, Iain arXiv https://doi.org/10.48550/arxiv.1705.07057	preprint	January 2017
i-RevNet: Deep Invertible Networks Jacobsen, Jörn-Henrik; Smeulders, Arnold; Oyallon, Edouard arXiv https://doi.org/10.48550/arxiv.1802.07088	text	January 2018
Hybrid Models with Deep and Invertible Features Nalisnick, Eric; Matsukawa, Akihiro; Teh, Yee Whye arXiv https://doi.org/10.48550/arxiv.1902.02767	preprint	January 2019
Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation Gabriel, Edgar; Fagg, Graham E.; Bosilca, George Recent Advances in Parallel Virtual Machine and Message Passing Interface https://doi.org/10.1007/978-3-540-30218-6_19	book	January 2004
3D variable-grid full-waveform inversion on GPU Wang, Zi-Ying; Huang, Jian-Ping; Liu, Ding-Jin Petroleum Science, Vol. 16, Issue 5 https://doi.org/10.1007/s12182-019-00368-2	journal	October 2019
Modeling the performance of large-scale CO2 storage systems: A comparison of different sensitivity analysis methods Wainwright, Haruko M.; Finsterle, Stefan; Zhou, Quanlin International Journal of Greenhouse Gas Control, Vol. 17 https://doi.org/10.1016/j.ijggc.2013.05.007	journal	September 2013
Modeling of time-lapse seismic monitoring using CO2 leakage simulations for a model CO2 storage site with realistic geology: Application in assessment of early leak-detection capabilities Wang, Zan; Harbert, William P.; Dilmore, Robert M. International Journal of Greenhouse Gas Control, Vol. 76 https://doi.org/10.1016/j.ijggc.2018.06.011	journal	September 2018
Learning representations by back-propagating errors Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. Nature, Vol. 323, Issue 6088 https://doi.org/10.1038/323533a0	journal	October 1986
Source-independent efficient wavefield inversion Song, Chao; Alkhalifah, Tariq Geophysical Journal International, Vol. 222, Issue 1 https://doi.org/10.1093/gji/ggaa196	journal	May 2020
Image Style Transfer Using Convolutional Neural Networks Gatys, Leon A.; Ecker, Alexander S.; Bethge, Matthias 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2016.265	conference	June 2016
Deep Residual Learning for Image Recognition He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2016.90	conference	June 2016
Xception: Deep Learning with Depthwise Separable Convolutions Chollet, Francois 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2017.195	conference	July 2017
Image-to-Image Translation with Conditional Adversarial Networks Isola, Phillip; Zhu, Jun-Yan; Zhou, Tinghui 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2017.632	conference	July 2017
Deep Photo Style Transfer Luan, Fujun; Paris, Sylvain; Shechtman, Eli 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2017.740	conference	July 2017
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks Xu, Tao; Zhang, Pengchuan; Huang, Qiuyuan 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2018.00143	conference	June 2018
MobileNetV2: Inverted Residuals and Linear Bottlenecks Sandler, Mark; Howard, Andrew; Zhu, Menglong 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2018.00474	conference	June 2018
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices Zhang, Xiangyu; Zhou, Xinyu; Lin, Mengxiao 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2018.00716	conference	June 2018
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions Wu, Bichen; Wan, Alvin; Yue, Xiangyu 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2018.00951	conference	June 2018
MnasNet: Platform-Aware Neural Architecture Search for Mobile Tan, Mingxing; Chen, Bo; Pang, Ruoming 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2019.00293	conference	June 2019
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks Zhu, Jun-Yan; Park, Taesung; Isola, Phillip 2017 IEEE International Conference on Computer Vision (ICCV) https://doi.org/10.1109/ICCV.2017.244	conference	October 2017
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks Zhang, Han; Xu, Tao; Li, Hongsheng 2017 IEEE International Conference on Computer Vision (ICCV) https://doi.org/10.1109/ICCV.2017.629	conference	October 2017
TSM: Temporal Shift Module for Efficient Video Understanding Lin, Ji; Gan, Chuang; Han, Song 2019 IEEE/CVF International Conference on Computer Vision (ICCV) https://doi.org/10.1109/ICCV.2019.00718	conference	October 2019
Deep Learning for Seismic Inverse Problems: Toward the Acceleration of Geophysical Analysis Workflows Adler, Amir; Araya-Polo, Mauricio; Poggio, Tomaso IEEE Signal Processing Magazine, Vol. 38, Issue 2 https://doi.org/10.1109/MSP.2020.3037429	journal	March 2021
InversionNet: An Efficient and Accurate Data-Driven Full Waveform Inversion Wu, Yue; Lin, Youzuo IEEE Transactions on Computational Imaging, Vol. 6 https://doi.org/10.1109/TCI.2019.2956866	journal	January 2020
Deep-Learning Inversion of Seismic Data Li, Shucai; Liu, Bin; Ren, Yuxiao IEEE Transactions on Geoscience and Remote Sensing, Vol. 58, Issue 3 https://doi.org/10.1109/TGRS.2019.2953473	journal	March 2020
Multitask Learning for Super-Resolution of Seismic Velocity Model Li, Yinshuo; Song, Jianyong; Lu, Wenkai IEEE Transactions on Geoscience and Remote Sensing, Vol. 59, Issue 9 https://doi.org/10.1109/TGRS.2020.3034502	journal	September 2021
Image Quality Assessment: From Error Visibility to Structural Similarity Wang, Z.; Bovik, A. C.; Sheikh, H. R. IEEE Transactions on Image Processing, Vol. 13, Issue 4 https://doi.org/10.1109/TIP.2003.819861	journal	April 2004
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks Zhang, Han; Xu, Tao; Li, Hongsheng IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 41, Issue 8 https://doi.org/10.1109/TPAMI.2018.2856256	journal	August 2019
VelocityGAN: Subsurface Velocity Image Estimation Using Conditional Adversarial Networks Zhang, Zhongping; Wu, Yue; Zhou, Zheng 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) https://doi.org/10.1109/WACV.2019.00080	conference	January 2019
AddressNet: Shift-Based Primitives for Efficient Convolutional Neural Networks He, Yihui; Liu, Xianggen; Zhong, Huasong 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) https://doi.org/10.1109/WACV.2019.00134	conference	January 2019
Transmission + reflection anisotropic wave‐equation traveltime and waveform inversion Feng, Shihang; Schuster, Gerard T. Geophysical Prospecting https://doi.org/10.1111/1365-2478.12733	journal	December 2018
Inverse Problem Theory and Methods for Model Parameter Estimation Tarantola, Albert https://doi.org/10.1137/1.9780898717921	book	January 2005
The Lifting Scheme: A Construction of Second Generation Wavelets Sweldens, Wim SIAM Journal on Mathematical Analysis, Vol. 29, Issue 2 https://doi.org/10.1137/S0036141095289051	journal	March 1998
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
Three dimensional SEG/EAEG models — an update Aminzadeh, F.; Burkhard, N.; Long, J. The Leading Edge, Vol. 15, Issue 2 https://doi.org/10.1190/1.1437283	journal	February 1996
Seismic modeling Carcione, José M.; Herman, Gérard C.; ten Kroode, A. P. E. GEOPHYSICS, Vol. 67, Issue 4 https://doi.org/10.1190/1.1500393	journal	July 2002
Comparison of source-independent methods of elastic waveform inversion Xu, Kun; Greenhalgh, Stewart A.; Wang, MiaoYue GEOPHYSICS, Vol. 71, Issue 6 https://doi.org/10.1190/1.2356256	journal	November 2006
An overview of full-waveform inversion in exploration geophysics Virieux, J.; Operto, S. GEOPHYSICS, Vol. 74, Issue 6 https://doi.org/10.1190/1.3238367	journal	November 2009
Elastic full-waveform inversion application using multicomponent measurements of seismic data collection Vigh, Denes; Jiao, Kun; Watts, Dave GEOPHYSICS, Vol. 79, Issue 2 https://doi.org/10.1190/geo2013-0055.1	journal	March 2014
Estimation of acoustic macro models using a genetic full-waveform inversion: Applications to the Marmousi model Sajeva, Angelo; Aleardi, Mattia; Stucchi, Eusebio GEOPHYSICS, Vol. 81, Issue 4 https://doi.org/10.1190/geo2015-0198.1	journal	July 2016
Estimating a starting model for full-waveform inversion using a global optimization method Datta, Debanjan; Sen, Mrinal K. GEOPHYSICS, Vol. 81, Issue 4 https://doi.org/10.1190/geo2015-0339.1	journal	July 2016
Elastic reflection-based waveform inversion with a nonlinear approach Guo, Qiang; Alkhalifah, Tariq GEOPHYSICS, Vol. 82, Issue 6 https://doi.org/10.1190/geo2016-0407.1	journal	October 2017
3D forward modeling of upgoing and downgoing wavefields using Hilbert transform Zheng, Yikang; Wang, Yibo; Chang, Xu GEOPHYSICS, Vol. 83, Issue 1 https://doi.org/10.1190/geo2016-0637.1	journal	January 2018
Deep-learning inversion: A next-generation seismic velocity model building method Yang, Fangshu; Ma, Jianwei GEOPHYSICS, Vol. 84, Issue 4 https://doi.org/10.1190/geo2018-0249.1	journal	July 2019
Seismic velocity estimation: A deep recurrent neural-network approach Fabien-Ouellet, Gabriel; Sarkar, Rahul GEOPHYSICS, Vol. 85, Issue 1 https://doi.org/10.1190/geo2018-0786.1	journal	January 2020
Velocity model building with a modified fully convolutional network Wang, Wenlong; Yang, Fangshu; Ma, Jianwei SEG Technical Program Expanded Abstracts 2018 https://doi.org/10.1190/segam2018-2997566.1	conference	August 2018
Two-grid genetic algorithm full-waveform inversion Mazzotti, Alfredo; Bienati, Nicola; Stucchi, Eusebio The Leading Edge, Vol. 35, Issue 12 https://doi.org/10.1190/tle35121068.1	journal	December 2016
Deep-learning tomography Araya-Polo, Mauricio; Jennings, Joseph; Adler, Amir The Leading Edge, Vol. 37, Issue 1 https://doi.org/10.1190/tle37010058.1	journal	January 2018

Similar Records

Multiscale Data-Driven Seismic Full-Waveform Inversion With Field Data Study

Journal Article · Thu Sep 30 20:00:00 EDT 2021 · IEEE Transactions on Geoscience and Remote Sensing · OSTI ID:1827579

Related Subjects

58 GEOSCIENCES
Computer science
Convolution
Deep learning
Earth sciences
Image reconstruction
Kernel
Mathematics
Task analysis
Three-dimensional displays
Training

InversionNet3D: Efficient and Scalable Learning for 3-D Full-Waveform Inversion

Citation Formats

References (50)

Similar Records

Related Subjects