Intelligent velocity picking and uncertainty analysis based on the Gaussian mixture model

• Autorzy: Wang Xiaowei , Gao Yang , Chen Chang , Yuan Huan , Yuan Sanyi

Identyfikatory

DOI

10.1007/s11600-022-00859-8

• Języki publikacji: EN

Abstrakty

EN

The stacking velocity is often obtained manually. However, manually picking is inefficient and is easily affected by subjective factors such as the priori information and the experience of different processors. To enhance its objectivity, efficiency and consistency, we investigated an unsupervised clustering intelligent velocity picking method based on the Gaussian mixture model (GMM). This method can automatically pick the stacking velocity fast, and provide uncertainty analysis as a quality control. Combined with the geometry feature of energy clusters in velocity spectra, taking advantages of the geometric diversity of energy clusters, GMM can ft the energy clusters with different distributions more appropriately. Then, mean values of the final several submodels are located as the optimal velocity, and the multiples are avoided under the expert knowledge and geological rules. In addition, according to the covariance of submodels, we can derive the uncertainty analysis of the final time-velocity pairs, so as to indicate the reliability of picking velocity at different depths. Moreover, the automated interpreted velocity field is used for both normal moveout (NMO) correction and stacking. The comparison with the manual references is adopted to evaluate the quality of the unsupervised clustering intelligent velocity picking method. Both synthetic data and 3D field data have shown that the proposed unsupervised intelligent velocity picking method can not only achieve similar accuracy with manual results, but also get rid of multiples. Furthermore, compared with manual picking, it can significantly improve the efficiency and accuracy in identifying pore and cave structures, as well as indicating the uncertainty of time-velocity pairs by variance.

Słowa kluczowe

EN

unsupervised learning; Gaussian mixture model; uncertainty analysis; artificial intelligence; velocity picking

PL

uczenie bez nadzoru; model mieszaniny Gaussa; analiza niepewności; sztuczna inteligencja

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2022
• Tom: Vol. 70, no 6
• Strony: 2659--2673
• Opis fizyczny: Bibliogr. 37 poz.

Twórcy

autor

Wang Xiaowei

• Research Institute of Petroleum Exploration and Development-Northwest, Petrochina, Lanzhou 730000, China

autor

Gao Yang

• State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Changping 102249, Beijing, China

autor

Chen Chang

• Exploration and Development Institute of Liaohe Oilfeld Company, PetroChina, Panjin 124010, China

autor

Yuan Huan

• Research Institute of Petroleum Exploration and Development-Northwest, Petrochina, Lanzhou 730000, China

autor

Yuan Sanyi

• State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Changping 102249, Beijing, China

Bibliografia

• 1. Abbad B, Ursin B, Rappin D (2009) Automatic nonhyperbolic velocity analysis. Geophysics 74(2):U1–U12. https://doi.org/10.1190/1.3075144
• 2. Ahmad A, Hashmi S (2016) K-Harmonic means type clustering algorithm for mixed datasets. Appl Soft Comput 48:39–49. https://doi.org/10.1016/j.asoc.2016.06.019
• 3. AlAli A, Anifowose F (2021) Seismic velocity modeling in the digital transformation era: a review of the role of machine learning. J Pet Explor Prod Technol 1–14. https://doi.org/10.1007/s13202-021-01304-0
• 4. Bin Waheed U, Al-Zahrani S, Hanafy SM (2019) Machine learning algorithms for automatic velocity picking: K-means vs. DBSCAN. 89th Annual International Meeting, SEG, Expanded Abstracts, p 5110–5114. https://doi.org/10.1190/segam2019-3215809.1
• 5. Biswas R, Vassiliou A, Stomberg R, Sen MK (2019) Estimating normal moveout velocity using the recurrent neural network. Interpretation 7(4):T819–T827. https://doi.org/10.1190/int-2018-0243.1
• 6. Cameron M, Fomel S, Sethian J (2008) Time-to-depth conversion and seismic velocity estimation using time-migration velocity. Geophysics 73(5):205–210. https://doi.org/10.1190/1.2967501
• 7. Chen YQ (2018) Automatic semblance picking by a bottom-up clustering method. In: SEG maximizing asset value through artificial intelligence and machine learning, p 44–48. https://doi.org/10.1190/AIML2018-12.1
• 8. Cooke D, Bóna A, Hansen B (2009) Simultaneous time imaging, velocity estimation, and multiple suppression using local event slopes. Geophysics 74(6):WCA65–WCA73. https://doi.org/10.1190/1.3242751
• 9. Dempster AP (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc. https://doi.org/10.1111/j.2517-6161.1977.tb01600.x
• 10. Fabien-Ouellet G, Sarkar R (2020) Seismic velocity estimation: a deep recurrent neural-network approach. Geophysics 85(1):U21–U29. https://doi.org/10.1190/geo2018-0786.1
• 11. Goodfellow I, Bengio Y, Courville A (2016) Deep learning. The MIT press. https://doi.org/10.1007/s10710-017-9314-z
• 12. Hou A, Marfurt KJ (2002) Multicomponent prestack depth migration by scalar wavefield extrapolation. Geophysics 67(6):1886–1894. https://doi.org/10.1190/1.1527088
• 13. Hung CH, Chiou HM, Yang WN (2013) Candidate groups search for K-harmonic means data clustering. Appl Math Model 37(24):10123–10128. https://doi.org/10.1016/j.apm.2013.05.052
• 14. Jones IF, Ibbotson K, Grimshaw M, Plasterie P (1998) 3-D prestack depth migration and velocity model building. Lead Edge 17(7):897–906. https://doi.org/10.1190/1.1438063
• 15. Lang XZ, Grana D (2017) Geostatistical inversion of prestack seismic data for the joint estimation of facies and impedances using stochastic sampling from Gaussian mixture posterior distributions. Geophysics 82(4):M55–M65. https://doi.org/10.1190/geo2016-0670.1
• 16. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444. https://doi.org/10.1038/nature14539
• 17. Lubo D, Marfurt K, Jayaram V (2014) Statistical characterization and geological correlation of wells using automatic learning Gaussian mixture models. 84th Annual International Meeting, SEG, Expanded Abstracts, p 774–783. https://doi.org/10.15530/urtec-2014-1922498
• 18. Lumley DE (1997) Monte Carlo automatic velocity picks. Stanf Explor Proj 75:1–25
• 19. Ma Y, Ji X, Fei TW, Luo Y (2018) Automatic velocity picking with convolutional neural networks. 88th Annual International Meeting, SEG, Expanded Abstracts, p 2066–2070. https://doi.org/10.1190/segam2018-2987088.1
• 20. Martin GS, Wiley R, Marfurt KJ (2006) Marmousi2: an elastic upgrade for Marmousi. Lead Edge 25(2):156–166. https://doi.org/10.1190/1.2172306
• 21. Nemeth T, Wu CJ, Schuster GT (1999) Least-squares migration of incomplete reflection data. Geophysics 64(1):208–221. https://doi.org/10.1190/1.1444517
• 22. Nowakowska E, Koronacki J, Lipovetsky S (2015) Clusterability assessment for Gaussian mixture models. Appl Math Comput 256:591–601. https://doi.org/10.1016/j.amc.2014.12.038
• 23. Park MJ, Sacchi MD (2020) Automatic velocity analysis using convolutional neural network and transfer learning. Geophysics 85(1):V33–V43. https://doi.org/10.1190/geo2018-0870.1
• 24. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536. https://doi.org/10.1038/323533a0
• 25. Smith K (2017) Machine learning assisted velocity autopicking. 87th Annual International Meeting, SEG, Expanded Abstracts, p 5686–5690. https://doi.org/10.1190/segam2017-17684719.1
• 26. Song W, Ouyang YL, Zeng QC, Huang JQ (2018) Unsupervised machine learning: K-means clustering velocity semblance auto-picking. In 80th EAGE annual international meeting, extended abstracts. https://doi.org/10.3997/2214-4609.201800919
• 27. Takougang EMT, Bouzidi Y, Ali MY (2019) Characterization of small faults and fractures in a carbonate reservoir using waveform inversion, reverse time migration, and seismic attributes. J Appl Geophys 161:116–123. https://doi.org/10.1016/j.jappgeo.2018.12.012
• 28. Toldi JL (1989) Velocity analysis without picking. Geophysics 54(2):191–199. https://doi.org/10.1190/1.1442643
• 29. Velis D (2021) Simulated annealing velocity analysis: automating the picking process. Geophysics 86(2):V119–V130. https://doi.org/10.1190/geo2020-0323.1
• 30. Wang WL, McMechan GA, Ma JW, Xie F (2020) Automatic velocity picking from semblances with a new deep-learning regression strategy: comparison with a classification approach. Geophysics 86(2):U1–U13. https://doi.org/10.1190/geo2020-0423.1
• 31. Wang D, Yuan SY, Liu T, Li SJ, Wang SX (2021a) Inversion-based non-stationary normal moveout correction along with prestack high-resolution processing. J Appl Geophys 191:104379. https://doi.org/10.1016/j.jappgeo.2021.104379
• 32. Wang D, Yuan SY, Yuan H, Zeng HH, Wang SX (2021b) Intelligent velocity picking based on unsupervised clustering with the adaptive threshold constraint. Chin J Geophys 64(3):1048–1060. https://doi.org/10.6038/cjg2021O0305
• 33. Wilson H, Gross L (2019) Reflection-constrained 2D and 3D non-hyperbolic moveout analysis using particle swarm optimization. Geophys Prospect 67:550–571. https://doi.org/10.1111/1365-2478.12758
• 34. Yilmaz Ö (2001) Seismic data analysis: processing, inversion, and interpretation of seismic data. SEG. https://doi.org/10.1190/1.9781560801580
• 35. Yuan SY, Jiao XQ, Luo YN, Sang WJ, Wang SX (2022) Double-scale supervised inversion with a data-driven forward model for low-frequency impedance recovery. Geophysics 87(2):R165–R181. https://doi.org/10.1190/geo2020-0421.1
• 36. Zhang H, Zhu PM, Gu Y, Li XZ (2019) Automatic velocity picking based on deep learning.89th Annual International Meeting, SEG, Expanded Abstracts, p 2604–2608. https://doi.org/10.1190/segam2019-3215633.1
• 37. Zhu DH, Gibson R (2018) Seismic inversion and uncertainty quantification using transdimensional Markov chain Monte Carlo method. Geophysics 83(4):R321–R334. https://doi.org/10.1190/geo2016-0594.1

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).