Machine learning for seismic data analysis and processing
Palavras-chave:
seismic exploration, velocities, neural networksResumo
Machine learning is setting the pace in the advancement of data analysis in many fields of science, technology, and industry. In this context, seismic data processing and inversion are approached by strategies that extract the relevant information from the data almost automatically. Dictionary learning and neural networks are two common examples of algorithms capable of capturing the complex structures and patterns embedded in data and inferring or predicting certain information of interest from them. We use a residual dictionary denoising technique to attenuate the acquisition footprint in 3D seismic data. Besides, we demonstrate some progress in using a deep neural network to invert the seismic moment tensor in well-monitoring scenarios. Machine learning also includes global optimization techniques, such as simulated annealing and differential evolution. We explore how these two algorithms can automate processes in seismic exploration such as velocity analysis and well-tying, which are conventionally done by hand and are thus susceptible to user subjectivity and experience.
Downloads
Referências
Abassi, Mostafa, and Ali Gholami. 2018. “Automatic Nonhyperbolic Velocity Analyis by Polynomial Chaos Expansion.” Geophysics 86 (6): no. 6, U79–U88.
Abbad, Brahim, Bjørn Ursin, and Didier Rappin. 2009. “Automatic Nonhyperbolic Velocity Analysis.” Geophysics 74 (2): no. 2, U1–U12.
Alali, Abdulmohsen, Gabriel Machado, and Kurt J. Marfurt. 2018. “Attribute-Assisted Footprint Suppression Using a 2D Continuous Wavelet Transform.” Interpretation 6 (2): T457–T470. https://doi.org/10.1190/INT-2017-0175.1
Baig, Adam, and Ted Urbancic. 2010. “Microseismic moment tensors: A path to understanding frac growth.” The Leading Edge 29 (3): 320–24.
Beckouche, Simon, and Jianwei Ma. 2014. “Simultaneous Dictionary Learning and Denoising for Seismic Data.” Geophysics 79 (3): no. 3, A27–A31. https://doi.org/10.1190/geo2013-0382.1
Bennett, James, Stan Lanning, and others. 2007. “The Netflix Prize.” In Proceedings of Kdd Cup and Workshop, 2007:35. New York, NY, USA.
Binder, Gary. 2018. “Neural Networks for Moment-Tensor Inversion of Surface Microseismic Data.” In SEG Technical Program Expanded Abstracts 2018, 2917–21. Society of Exploration Geophysicists.
Bougher, Benjamin Bryan. 2016. “Machine Learning Applications to Geophysical Data Analysis.” PhD thesis, University of British Columbia.
Brunini, Germán I., Danilo R. Velis, and Juan I. Sabbione. 2021. “Seismic Moment Tensor Inversion in Anisotropy Media Using Deep Neural Networks.” In Anales, 5 pages. San Juan, Argentina.
Chen, Yangkang. 2018. “Automatic Velocity Analysis Using High-Resolution Hyperbolic Radon Transform.” Geophysics 83 (4): no. 4, A53–A57.
Chopra, Satinder, and Glen Larsen. 2000. “Acquisition Footprint–Its Detection and Removal.” CSEG Recorder 25 (8): 16–20.
Davis, L., ed. 1987. Genetic Algorithms and Simulated Annealing. Los Altos, CA: Morgan Kaufmann Publishers.
Drummond, J. M., Arthur J. L. Budd, and James W. Ryan. 2000. “Adapting to Noisy 3D Data - Attenuating the Acquisition Footprint.” SEG Technical Program Expanded Abstracts, 9–12. https://doi.org/10.1190/1.1816247
Elad, Michael. 2010. Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing. Springer Science & Business Media.
Falconer, Scott, and Kurt J. Marfurt. 2008. “Attribute-Driven Footprint Suppression.” SEG Technical Program Expanded Abstracts, 2667–71. https://doi.org/10.1190/1.3063897
Fortini, Carlo, Davide Maggi, Vincenzo Lipari, and Maurizio Ferla. 2013. “Particle Swarm Optimization for Seismic Velocity Analysis.” In Expanded Abstracts, 4864–8. SEG.
Garabito, German. 2018. “Global Optimization Strategies for Implementing 3D Common-Reflection-Surface Stack Using the Very Fast Simulated Annealing Algorithm: Application to Real Land Data.” Geophysics 83 (4): no. 4, V253–V261.
Gelpi, Gabriel, Daniel O. Pérez, and Danilo R. Velis. 2020. “Automatic Well Tying and Wavelet Phases Estimation with No Waveform Stretching or Squeezing.” Geophysics 85 (3): D83–D91.
Goldberg, D. E., ed. 1989. Genetics Algorithms in Search, Optimization, and Machine Learning. Addisson-Wesley Publishing Company, Inc.
Gómez, Julián L., and Danilo R. Velis. 2020. “Footprint Removal from Seismic Data with Residual Dictionary Learning.” Geophysics 85 (4): V355–V365. https://doi.org/10.1190/geo2019-0482.1
Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT press.
Grechka, Vladimir. 2015. “On the Feasibility of Inversion of Single-Well Microseismic Data for Full Moment Tensor.” Geophysics 80 (4): KS41–KS49.
Grechka, Vladimir, and Werner M. Heigl. 2017. Microseismic Monitoring. Society of Exploration Geophysicists, Tulsa, OK. https://doi.org/10.1190/1.9781560803485
Grechka, Vladimir I. 2015. “Moment Tensor Inversion of Single-Well Microseismic Data: Is It Feasible?” In SEG Technical Program Expanded Abstracts 2015, 2506–11. Society of Exploration Geophysicists.
Gülünay, Necati. 1999. “Acquisition Geometry Footprints Removal.” SEG Technical Program Expanded Abstracts, 637–40. https://doi.org/10.1190/1.1821103
Gülünay, Necati, F. Martin, and R. Martinez. 1994. “3D Data Acquisition Artifacts Removal by Spot Editing in the Spatial-Temporal Frequency Domain.” 56th Annual International Conference and Exhibition, EAGE, Extended Abstracts, H049.
Herrera, H., S. Fomel, and M. van der Baan. 2014. “Automatic Approaches for Seismic to Well Tying.” Interpretation 2 (2): SD101–SD109.
Herron, D. 2011. First Steps in Seismic Interpretation. Society of Exploration Geophysicists. https://doi.org/10.1190/1.9781560802938
Ingber, L. 1989. “Very Fast Simulated Re-Annealing.” Journal of Mathematical Computation and Modelling 12: 967–73.
Kirkpatrick, S., C. D. Jr. Gellat, and M. P. Vecchi. 1983. “Optimization by Simulated Annealing.” Science 220: 671–80.
Laarhoven, P. I. M. van, and E. H. L. Aarts. 1988. Simulated Annealing: Theory and Applications. Dordrecht: D. Riedel.
Li, Chengbo, Yu Zhang, and Charles C. Mosher. 2019. “A Hybrid Learning-Based Framework for Seismic Denoising.” The Leading Edge 38 (7): 542–49. https://doi.org/10.1190/tle38070542.1
Mallat, Stephane. 1999. A Wavelet Tour of Signal Processing: The Sparse Way. 3rd ed. Academic Press.
Marfurt, Kurt J., Ronald M. Scheet, John A. Sharp, and Mark G. Harper. 1998. “Suppression of the Acquisition Footprint for Seismic Sequence Attribute Mapping.” Geophysics 63 (3): 1024–35. https://doi.org/10.1190/1.1444380
Muñoz, A., and D. Hale. 2015. “Automatic Simultaneous Multiple Well Ties.” Geophysics 80 (8): IM45–IM51.
Newrick, R. 2012. Well Tie Perfection - 52 Things You Should Know About Geophysics. Agile Libre.
Ovcharenko, Oleg, Jubran Akram, and Daniel Peter. 2018. “Feasibility of Moment Tensor Inversion from a Single Borehole Data Using Artificial Neural Networks.” Search and Discovery.
Park, Min Jun, and Mauricio D. Sacchi. 2020. “Automatic Velocity Analysis Using Convolutional Neural Network and Transfer Learning.” Geophysics 85 (1): no. 1, V33–V43. https://doi.org/10.1190/geo2018-0870.1
Qadrouh, AN, JM Carcione, M Alajmi, and MM Alyousif. 2019. “A Tutorial on Machine Learning with Geophysical Applications.” Bollettino Di Geofisica Teorica Ed Applicata 60 (3).
Sahai, Surinder K, and Khalid A Soofi. 2006. “Use of Simple 2-D Filters to Reduce Footprint Noise in Seismic Data.” Geohorizons 7: 14–17.
Samuel, Arthur L. 1959. “Some Studies in Machine Learning Using the Game of Checkers.” IBM Journal of Research and Development 3 (3): 210–29.
Simm, R., and M. Bacon. 2014. “Seismic Amplitude: An Interpreter’s Handbook.” In. Cambridge University Press.
Soubaras, Robert. 2002. “Attenuation of Acquisition Footprint for Non-Orthogonal 3D Geometries.” SEG Technical Program Expanded Abstracts, 2142–5. https://doi.org/10.1190/1.1817129
Sripanich, Yanadet, Sergey Fomel, Jeannot Trampert, William Burnett, and Thomas Hess. 2020. “Probabilistic Moveout Analysis by Time Warping.” Geophysics 85 (1): no. 1, U1–U20.
Storn, R., and K. Price. 1997. “Differential Evolution – a Simple and Efficient Heuristic for Global Optimization over Continuous Spaces.” Journal of Global Optimization 11: 341–59.
Tošić, Ivana, and Pascal Frossard. 2011. “Dictionary Learning: What Is the Right Representation for My Signal?” IEEE Signal Processing Magazine 28 (2): 27–38.
Turquais, Pierre, Endrias G. Asgedom, and Walter Söllner. 2017a. “A Method of Combining Coherence-Constrained Sparse Coding and Dictionary Learning for Denoising.” Geophysics 82 (3): V137–V148. https://doi.org/10.1190/geo2016-0164.1
———. 2017b. “Coherent Noise Suppression by Learning and Analyzing the Morphology of the Data.” Geophysics 82 (6): V397–V411. https://doi.org/10.1190/geo2017-0092.1
Vavryčuk, Václav, and Daniela Kühn. 2012. “Moment Tensor Inversion of Waveforms: A Two-Step Time-Frequency Approach.” Geophysical Journal International 190 (3): 1761–76.
Velis, Danilo R. 2021. “Simulated Annealing Velocity Analysis: Automating the Picking Process.” Geophysics 86 (6).
Walden, A. T., and R. E. White. 1984. “On Errors of Fit and Accuracy in Matching Synthetic Seismograms and Seismic Traces.” Geophysical Prospecting 32: 871–91.
Wamriew, Daniel Stephen, Marwan Charara, Evgenii Maltsev, and others. 2020. “Deep Neural Network for Real-Time Location and Moment Tensor Inversion of Borehole Microseismic Events Induced by Hydraulic Fracturing.” In SPE Russian Petroleum Technology Conference. Society of Petroleum Engineers.
White, R., and R. Simm. 2003. “Tutorial: Good Practice in Well Ties.” EAGE First Break 21: 75–83.
Yilmaz, Özdoân. 2001. Seismic Data Analysis: Processing, Inversion, and Interpretation of Seismic Data. Investigations in Geophysics. SEG.
Ziolkowski, A., J. R. Underhill, and R. G. K. Johnston. 1998. “Wavelets, Well Ties, and the Search for Subtle Stratigraphic Traps.” Geophysics 63 (1): P297–P313.
Zu, Shaohuan, Hui Zhou, Rushan Wu, Maocai Jiang, and Yangkang Chen. 2019. “Dictionary Learning Based on Dip Patch Selection Training for Random Noise Attenuation.” Geophysics 84 (3): V1–V15. https://doi.org/10.1190/geo2018-0596.1
Downloads
Publicado
Como Citar
Edição
Seção
Licença
![Creative Commons License](http://i.creativecommons.org/l/by-nc-sa/4.0/88x31.png)
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
A partir de 2022 (Vol. 43 número 2) os artigos serão publicados na revista sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
De acordo com esses termos, o material pode ser compartilhado (copiado e redistribuído em qualquer meio ou formato) e adaptado (remixado, transformado e criado a partir do material outra obra), desde que a) a autoria e a fonte original de sua publicação (revista e URL da obra), b) não é utilizado para fins comerciais ec) os mesmos termos de licença são mantidos.
Antes desta data os artigos foram publicados na revista sob uma licença Creative Commons Attribution (CC BY)
Em ambos os casos, a aceitação dos originais pela revista implica a cessão não exclusiva dos direitos patrimoniais dos autores em favor do editor, que permite a reutilização, após edição (postprint), sob a licença que corresponde de acordo com a edição. .
Tal atribuição significa, por um lado, que após a sua publicação (postprint) na Revista GEOACTA da Associação de Geofísicos e Geodesistas, os autores podem publicar o seu trabalho em qualquer idioma, suporte e formato (nestes casos, solicita-se que fique registrado que o material foi publicado originalmente nesta revista); por outro, a autorização dos autores para que o trabalho seja colhido por SEDICI, o repositório institucional da Universidade Nacional de La Plata, e divulgado nas bases de dados que a equipe editorial considere adequadas para aumentar a visibilidade da publicação e seus autores.
Da mesma forma, a revista incentiva os autores para que após sua publicação na Revista da Associação de Geofísicos e Geodesistas, depositem suas produções em outros repositórios institucionais e temáticos, sob o princípio de que oferecer à sociedade produção científica e bolsa acadêmica irrestrita contribui para uma maior intercâmbio de conhecimento global.