1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 68, Issue 2
  5. Article
Volume 68, Issue 2
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

Saltbodies are important subsurface structures that have significant implications for hydrocarbon accumulation and sealing in petroleum reservoirs, and accurate saltbody imaging and delineation is now greatly facilitated with the availability of three‐dimensional seismic surveying. However, with the growing demand for larger survey coverage and higher imaging resolution, the size of seismic data is increasing dramatically. Correspondingly, manual saltbody interpretation fails to offer an efficient solution, particularly in exploration areas of complicated salt intrusion history. Recently, artificial intelligence is attracting great attention from geoscientists who desire to utilize the popular machine learning technologies for evolving the interpretational tools capable of mimicking an experienced interpreter's intelligence. This study first implements two popular machine learning tools, the multi‐layer perceptron and the convolutional neural network, for delineating seismic saltbodies at sample and pattern levels, respectively, then compares their performance through applications to the synthetic SEAM seismic volume, and moreover tentatively investigates what contributes to the better convolutional neural network delineation. Specifically, the multi‐layer perceptron scheme is capable of efficiently utilizing an interpreter's knowledge by selecting, pre‐conditioning and integrating a set of seismic attributes that best highlight the target saltbodies, whereas the convolutional neural network scheme makes it possible for saltbody delineation directly from seismic amplitude and thus significantly reduces the dependency on attribute selection from interpreters. It is concluded that the better performance from the convolutional neural network scheme results from two factors. First, the convolutional neural network builds the mapping relationship between the seismic signals and the saltbodies using the original seismic amplitude instead of manually selected seismic attributes, so that the negative impact of using less representative attributes is virtually eliminated. Second and more importantly, the convolutional neural network defines, learns and identifies the saltbodies by utilizing local seismic reflection patterns, so that the seismic noises and processing artefacts of distinct patterns are effectively identified and excluded.

© 2020 European Association of Geoscientists & Engineers © 2019 European Association of Geoscientists & Engineers
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.12865
2019-09-23
2024-04-26

  • From This Site

    /content/journals/10.1111/1365-2478.12865
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Al‐DossaryS. and MarfurtK.J.2006. 3D volumetric multispectral estimates of reflector curvature and rotation. Geophysics71, 41–51.
     [Google Scholar]
  2. AminA. and DericheM.2015. A new approach for salt dome detection using a 3D multidirectional edge detector. Applied Geophysics12, 334–342.
     [Google Scholar]
  3. AqrawiA.A., BoeT.H. and BarrosS.2011. Detecting salt domes using a dip guided 3D Sobel seismic attribute. SEG Technical Program, San Antonio, TX, Expanded Abstracts, 1014–1018.
  4. BahorichM. and FarmerS.1995. 3‐D seismic coherency for faults and stratigraphic features. The Leading Edge14, 1053–1058.
     [Google Scholar]
  5. BerthelotA., SolbergA.H. and GeliusL.J.2013. Texture attributes for detection of salt. Journal of Applied Geophysics88, 52–69.
     [Google Scholar]
  6. ChavesM.U., OliverF., KawakamiG. and Di MarcoL.2011. Visualization of geological features using seismic volume rendering, RGB blending and geobody extraction, 12th International Congress of the Brazilian Geophysical Society & EXPOGEF, Rio de Janeiro, Brazil, 848–850.
  7. ChopraS. and MarfurtK.J.2005. Seismic attributes – a historical perspective. Geophysics70, 3SO–28SO.
     [Google Scholar]
  8. DiH. and AlRegibG.2017. Seismic multi‐attribute classification for salt boundary detection: A comparison. 79th EAGE Conference and Exhibition, Tu‐B4‐13, Paris, France.
  9. DiH. and GaoD.2014. Gray‐level transformation and Canny edge detection for 3D seismic discontinuity enhancement. Computers & Geosciences72, 192–200.
     [Google Scholar]
  10. DiH. and GaoD.2017a. 3D seismic flexure analysis for subsurface fault detection and fracture characterization. Pure and Applied Geophysics174, 747–761.
     [Google Scholar]
  11. DiH. and GaoD.2017b. Nonlinear gray‐level co‐occurrence matrix texture analysis for improved seismic facies interpretation. Interpretation5, SJ31–SJ40.
     [Google Scholar]
  12. DiH., GaoD. and AlRegibG.2019. Developing a seismic texture analysis network for automated seismic pattern recognition and classification. Geophysical Journal International218, 1262–1275.
     [Google Scholar]
  13. DiH., ShafiqM.A. and AlRegibG.2017. Seismic fault detection based on multi‐attribute support vector machine analysis. SEG Technical Program, Extended Abstracts, 2039–2044.
  14. DiH., ShafiqM. and AlRegibG.2018. Multi‐attribute k‐means clustering for salt boundary detection from 3D seismic data. Geophysical Journal International215, 1999–2007.
     [Google Scholar]
  15. DiH., ShafiqM.A., WangZ. and AlRegibG.2019. Improving seismic fault detection by a super‐attribute‐based classification. Interpretation7, SE251–SE267.
     [Google Scholar]
  16. DiH., WangZ. and AlRegibG.2018a. Deep convolutional neural networks for seismic salt‐body delineation. AAPG Annual Convention and Exhibition Search and Discovery, Salt Lake City, Utah.
  17. DiH., WangZ. and AlRegibG.2018b. Why using CNN for seismic interpretation? An investigation. 88th Annual SEG meeting, Anaheim, CA, Extended Abstracts, 2216–2220.
  18. DrissiN., ChonavelT. and BoucherJ.2008. Salient features in seismic images. OCEANS 2008 – MTS/IEEE Kobe Techno‐Ocean, Kobe, Japan, 1–4.
  19. DuvalG., MannJ. and HoustonL.2015. Angola, Kwanza Basin: exploring further and deeper. GeoExPro Vol. 10.
  20. EichkitzC.G., AmtmannJ. and SchreilechnerM.G.2013. Calculation of gray level co‐occurrence matrix‐based seismic attributes in three dimensions. Computers & Geosciences60, 176–183.
     [Google Scholar]
  21. FehmersG.C. and HöckerC.F.2003. Fast structural interpretation with structure‐oriented filtering. Geophysics68, 1286–1293.
     [Google Scholar]
  22. Fellbaum, C.2005. Wordnet and wordnets. In: Encyclopedia of Language and Linguistics, 2nd edn (eds K.Brownet al.), pp. 665–670. Elsevier, Oxford.
     [Google Scholar]
  23. FossenH.2016. Structural Geology. Cambridge University Press.
     [Google Scholar]
  24. GaoD.2003. Volume texture extraction for 3D seismic visualization and interpretation. Geophysics68, 1294–1302.
     [Google Scholar]
  25. GaoD.2013. Integrating 3D seismic curvature and curvature gradient attributes for fracture detection: methodologies and Interpretational implications. Geophysics78, O21–O38.
     [Google Scholar]
  26. GuillenP., LarrazabalG., GonzalezG., BoumberD. and VilaltaR.2015. Supervised learning to detect salt body. SEG Technical Program, Expanded Abstracts, 1826–1829.
  27. GuittonA., WangH. and GuittonW.T.2017. Statistical imaging of faults in 3D seismic volumes using a machine learning approach. SEG Technical Program, Expanded Abstracts, 2045–2049.
  28. HahnloserR.H., SarpeshkarR., MahowaldM.A., DouglasR.J. and SeungH.S.2000. Digital selection and analogue amplification coexist in a cortex‐inspired silicon circuit. Nature405, 947–951.
     [Google Scholar]
  29. HalpertA.D., ClappR.G. and BiondiB.2014. Salt delineation via interpreter‐guided 3D seismic image segmentation. Interpretation2, T79–T88.
     [Google Scholar]
  30. HegazyT. and AlRegibG.2014. Texture attributes for detecting salt bodies in seismic data. SEG Technical Program, Expanded Abstracts, 1455–1459.
  31. HintonG.E., SrivastavaN., KrizhevskyA., SutskeverI. and SalakhutdinovR.R.2012. Improving neural networks by preventing co‐adaptation of feature detectors. Preprint, arXiv1207.0580.
  32. HuangL., DongX. and CleeT.E.2017. A scalable deep learning platform for identifying geologic features from seismic attributes. The Leading Edge36, 249–256.
     [Google Scholar]
  33. JiS., XuW., YangM. and YuK.2013. 3D convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence35, 221–231.
     [Google Scholar]
  34. LeCunY., BottouL., BengioY. and HaffnerP.1998. Gradient‐based learning applied to document recognition. Proceedings of the IEEE86, 2278–2324.
     [Google Scholar]
  35. LinT.Y., MaireM., BelongieS., BourdevL., GirshickR., HaysJ., PeronaP., RamananD., DollarP. and ZitnickC.L.2014. Microsoft COCO: Common Objects in Context. In: Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, Vol. 8693 (eds. D.Fleet, T.Pajdla, B.Schiele and T.Tuytelaars). Springer, Cham.
     [Google Scholar]
  36. LongJ., ShelhamerE. and DarrellT.2015. Fully convolutional networks for semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Wellington, New Zealand, 3431–3440.
  37. LuoY., HiggsW.G. and KowalikW.S.1996. Edge detection and stratigraphic analysis using 3‐D seismic data. SEG Technical Program, Expanded Abstracts, 324–327.
  38. MarfurtK.J., KirlinR.L., FarmerS.L. and BahorichM.S.1998. 3‐D seismic attributes using a semblance‐based coherency algorithm. Geophysics63, 1150–1165.
     [Google Scholar]
  39. MatsuguM., MoriK., MitariY. and KanedaY.2003. Subject independent facial expression recognition with robust face detection using a convolutional neural network. Neural Networks16, 555–559.
     [Google Scholar]
  40. MaturanaD. and SchererS.2015. Voxnet: a 3D convolutional neural network for real‐time object recognition, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, 922–928.
  41. McCormackM.D.1991. Neural computing in geophysics. The Leading Edge10, 11–15.
     [Google Scholar]
  42. MeldahlP., HegglandR., BrilB. and de GrootP.1999. The chimney cube, an example of semi‐automated detection of seismic objects by directive attributes and neural networks: part I: methodology. SEG Technical Program, Expanded Abstracts, 931–934.
  43. NairV. and HintonG.2010. Rectified linear units improve restricted Boltzmann machines. Proceedings of the 27th International Conference on Machine Learning, 807–814.
  44. OristaglioM.2016. SEAM update – integrated reservoir and geophysical modeling: SEAM time lapse and SEAM life of field. The Leading Edge35, 912–915.
     [Google Scholar]
  45. QiJ., LinT., ZhaoT., LiF. and MarfurtK.2015. Semisupervised multiattribute seismic facies analysis. Interpretation4, SB91–SB106.
     [Google Scholar]
  46. RenS., HeK., GirshickR. and SunJ.2015. Faster R‐CNN: towards real‐time object detection with region proposal networks. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, 91–99.
  47. RobertsA.2001. Curvature attributes and their application to 3D interpreted horizons. First Break19, 85–100.
     [Google Scholar]
  48. ShafiqM.A., AlshawiT., LongZ. and AlRegibG.2016. SAISI: a new seismic attribute for salt dome detection. ICASSP, Barcelona, Spain, 1876–1880.
  49. ShafiqM.A., WangZ., AminA., HegazyT., DericheM. and AlRegibG.2015. Detection of salt‐dome boundary surfaces in migrated seismic volumes using gradient of textures. SEG Technical Program, Expanded Abstracts, 1811–1815.
  50. ShiY., WuX. and FomelS.2019. SaltSeg: automatic 3D salt segmentation using a deep convolutional neural network. Interpretation7, SE113–SE122.
     [Google Scholar]
  51. TingdahlK.M. and de RooijM.2005. Semi‐automatic detection of faults in 3D seismic data. Geophysical Prospecting53, 533–542.
     [Google Scholar]
  52. van VlietL.J. and VerbeekP.W.1995. Estimators for orientation and anisotropy in digitized images, Proceedings of the first annual conference of the Advanced School for Computing and Imaging ASCI’95, 442–450.
  53. WaldelandA.U., JensenA.C., GeliusL.J. and SolbergA.H.S.2018. Convolutional neural networks for automated seismic interpretation. The Leading Edge37, 529–537.
     [Google Scholar]
  54. WangZ., HegazyT., LongZ. and AlRegibG.2015. Noise‐robust detection and tracking of salt domes in postmigrated volumes using texture, tensors, and subspace learning. Geophysics80, WD101–WD116.
     [Google Scholar]
  55. WeickertJ.1997. A review of nonlinear diffusion filtering. In: Scale‐Space Theory in Computer Vision (eds. B.ter Haar Romeny, L.Florack, J.Koenderink and M.Viergever), pp. 3–28. Springer, Berlin.
     [Google Scholar]
  56. WuX.2016. Methods to compute salt likelihoods and extract salt boundaries from 3D seismic images. Geophysics81, IM119–IM126.
     [Google Scholar]
  57. WuX., FomelS. and HudecM.2018. Fast salt boundary interpretation with optimal path picking. Geophysics83, O45–O53.
     [Google Scholar]
  58. YangL., HannekeS. and CarbonellJ.2013. A theory of transfer learning with applications to active learning. Machine learning90, 161–189.
     [Google Scholar]
  59. ZengY., JiangK. and ChenJ.2018. Automatic seismic salt interpretation with deep convolutional neural networks. Preprint, arXiv 1812.01101.
  60. ZhengZ., KavousiP. and DiH.2014. Multi‐attributes and neural network‐based fault detection in 3D seismic interpretation. Advanced Materials Research838, 1497–1502.
     [Google Scholar]
  61. ZhouJ., ZhangY., ChenZ. and LiJ.2007. Detecting boundary of salt dome in seismic data with edge detection technique. SEG Technical Program, Expanded Abstracts, 1392–1396.
http://instance.metastore.ingenta.com/content/journals/10.1111/1365-2478.12865
Loading
A comparison of seismic saltbody interpretation via neural networks at sample and pattern levels
Geophysical Prospecting 68, 521 (2020); https://doi.org/10.1111/1365-2478.12865
/content/journals/10.1111/1365-2478.12865
/content/journals/10.1111/1365-2478.12865
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Computing aspects; Interpretation; Seismics

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error