Cite this article
1
Download
49
Views
Journal Browser
Volume | Year
Issue
Search
News and Announcements
View All
ARTICLE

Effective detection of seismic events detection by non-classical receptive field visual cognitive modeling

JING ZHAO1 HAOJIE LEI1 YANG LI1 JINCHANG REN2* GENYUN SUN3 HUJIMIN ZHAO4 HONGYAN SHEN5 DAXING WANG5
Show Less
2 National Subsea Centre, Robert Gordon University, Aberdeen AB10 7QB, U.K.,
3 School of Geosciences, China University of Petroleum (East China), Qingdao 266580, P. R. China.,
4 School of Computer Sciences, Guangdong Polytechnic Normal University, Guangzhou 510450, P.R. China.,
JSE 2023, 32(4), 385–406;
Submitted: 9 April 2023 | Accepted: 4 July 2023 | Published: 1 August 2023
© 2023 by the Authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

Zhao, J.. Lei, H.J., Li, Y.. Ren, J.C:, Sun, G.Y., Zhao, H.M.. Shen, H.Y. and Wang. D.X.. 2023. Effective detection of seismic events by non-classical receptive field visual cognitive modeling. Journal of Seismic Exploration, 32: 385-406. The detection and up-picking of the seismic events are critical for seismic data analysis and interpretation. Events picking can be used for sequence stratigraphic analysis, reservoir feature extraction, the determining of the subsequent reflection interface, the improving of the SNR and the storage prediction. The research of the events picking is very significant for the seismic exploration. In order to overcome the existing events picking methods have the same sensitivity to noise. we propose a non-classical receptive field visual cognitive method for the events picking up. Vision is an important functional organ for human beings to observe and recognize the world. About 80% of the information obtained by human beings from the outside world comes from the visual system, which fully shows that visual information is huge. and also shows that human beings have a high utilization rate of visual information. How to transfer some typical information processing mechanism and target recognition function of human vision to machine is one of the most important and urgent tasks in the field of computer vision and artificial intelligence. The introduction of computer vision technology into geophysical prospecting is still in its infancy in the field of seismic exploration, our research fill the blank of this field. where the use of visual features to improve the seismic data processing and rapid realization of oil and gas exploration, will become the vane of the future direction of research and development. As a basic research work in the crossing field. this paper has made a breakthrough in the research methods and ideas, and the research content can be summarized as the following four aspects: 1. The proposed method implements the function of environmental suppression and spatial enhancement of the bio-visual primary visual cortex, which is applies to the pre-stack seismic data. as pre-stack seismic data contains abundant information such as amplitude and frequency to reflect tiny structures of the formation. 2. The seismic data is preprocessed to obtain the wavelet fusion of the envelope peak instantaneous frequency (EPIF) and the slant stack peak amplitude (SSPA), which can maximum the limit to provide optimal quality data. 3. An adaptive Gabor filter direction selection method is proposed to provide a reliable angle range and improve the recognition rate of filter decomposition. In addition, by adopting an anisotropic environmental suppression method, our method can detect edge variability more accurately than the isotropic method. 4. With the enhanced contour aggregation. cocircular constraint is adopted and combined with the characteristics of low curvature and continuous changing curvature. which is unique to the seismic events. to establish a consistent spatial structure perception model. The events picked by our method is more continuous and accurate than the existing methods. and doesn't require human interaction, which is beneficial for subsequent seismic interpretation and reservoir prediction.

Keywords
non-classical receptive field
events picking
pre-stack seismic data
environmental suppression
spatial enhancement
Gabor filter
cocircular constraint
References
  1. Bondar, A., 1992. Seismic horizon detection using image processing algorithms.Geophys. Process.. 40: 785-800.
  2. Canny, J.. 1986. A Computational approach to edge detection. IEEE Transact. PatternAnalys. Machine Intellig., PAMI-8(6): 679-698.
  3. Chang, C. and Chatterjee, S., 1993. Ranging through Gabor logonsa consistent,hierarchical approach. IEEE Transact. Neural Netw, 4: 827-843.
  4. Clark, G.A., Glinsky, M.E., Devi, K.R.S., Robinson, J.H. and Ford, G.E., 1996.
  5. Automatic event picking in pre-stack migrated gathers using a probabilistic neuralnetwork. Geophysics. 66: 1488-1496.
  6. Ding, W.F., Pan, G., Gou, Z.K., Fu, X.M., Zhang, J. and Hu, T., 2012. The research ofinteractive auto pickup of seismic events based on energy ratio and cross-correlation.Acta Oceanol. Sinica, 34(3): 87-91.
  7. Feng, W.K., Friedt, J.M., Cherniak, G., Hu, Z.P., Sato, M., 2019. Direct path interferencesuppression for short-range passive bistatic synthetic aperture radar imaging based onatomic norm minimisation and Vandermonde decomposition. IET Radar, Sonar &Navigation, 13(7): 1171-1179.
  8. Folsom, T.C. and Pinter, R.B., 1998. Primitve features by steering, quadrature, and scale.
  9. IEEE Transact. Pattern Analys. Machine Intellig,, 20: 1161-1173.
  10. Grigorescu, S.E., Petkov. N. and Kruizinga, P.. 2002. Comparison of texture featuresased on Gabor filters, IEEE Transact. Image Process., 11: 1160-1167.
  11. Grossberg, S. and Mingolla, E., 1985. Neural dynamics of perceptual grouping: textures,boundaries and emergent segmentatios. Percept. Psychophys, 38: 141-171.
  12. Grossberg, S. and Carpenter, G.A., 2003. Adaptive Resonance Theory, Handbook of
  13. Brain Theory and Neural Networks, 2nd ed. (M.A. Arbib, ed.), Cambridge, MITPress: 87-90.
  14. Haralick, R.M.. 1984. Digital step edges from zero crossing of second directionalderivatives. IEEE Transact. Pattern Analys. Machine Intellig., PAMI-6: 58-68.
  15. Huang, C., Zhang, D.L., Sun, D. and Lan, H.L., 2014. Direct path interferencesuppression based on zero constraint condition with phase correction. J. HarbinEngineer. Univ., 35: 1224-1230.
  16. Jin, L., 2010. Visual cognition based recognition of objects in natural images. ChongqingUniversity, Chongqing.
  17. Li, H.-X., Liu, C. and Tao, C.H., 2007. The study of application of edge measuringtechnique to the detection of phase axis of the seismic section. Progr. Geophysics,22: 1607-1610.
  18. Li, X. 2014. Automatic seismic event pickup using edge measuring technique. OceanUniversity of China, Qingdao.
  19. Lu, J.M., 1993. Principles of Seismic Exploration. China University of Petroleum Press,Qingdao.
  20. McComack, M.D., 1993. First-break refraction event picking and seismic data traceediting using neural network. Geophysics, 58: 67.
  21. Milanova, M.G., Elmaghraby, A.S., Wachowiak, M.P. and Campilho. A., 2000. Acomputational model of visual cortex receptive fields using spatio-temporal filters.
  22. Proc. 2000 IEEE/EMBS Conf. Informat. Technol. Applicat. Biomed.: 129-134.
  23. Ning, J.-S., Wang, H.-H. and Luo, Z.-C., 2005. Downward continuation of gravitysignals based on the multiscale edge constraint. Chinese J. Geophys. (In Chinese),48: 63-68.
  24. Petkov. N.. 1995. Biologically motivated computationally intensive approaches to imagepattern recognition. Future Generation Comput. Systems. 11: 451-465.
  25. Petkov. N. and Subramanian. E.. 2007. Motion detection, noise reduction, texturesuppression and contour enhancement by spatiotemporal Gabor filters withsurround inhibition. Biological Cybernetics, 97 (5-6): 423-439.
  26. Petkov. N. and Wieling. M.B.. 2017. Gabor filtering augmented with surround inhibitionfor improved contour detection by texture suppression. Perception,33(supvlement):38c.
  27. Shi, W., Lin, C.H.. Wang, W.H. and Gao. Y.L.. 2019. A first arrival pickup method ofmicro-seismic event based on statistic energy ratio using varied time window withdouble constraints. Geophys. Geochem. Explor., 43: 1064-1073.
  28. Spagnolini. U., 1991. Adaptive picking of refracted first arrivals. Geophys. Prosp., 39:293-312.
  29. Stankovic, S. Diurovic. I. and Pitas. I. 2001. Watermarking in the space/spatialfrequency domain using two-dimensional Radon-Wigner distribution. IEE
  30. Transact. Image Process. IEEE Sign. Process. Soc.. 10(4): 650-8.
  31. St-Onge. A.. 2011. Akaike information criterion applied to detecting first arrival timeson microseismic data. CSPG CSEG CWLS Convention: 1-5.
  32. Tabatabai, A.J. and Mitchell. O.R.. 2009. Edge location to subpixel values in digitalimagery. IEEE Transact, Pattern Analys. Machine Intellig., PAM/-6(2), 188-201.
  33. Tu, P., Mason, I. and Zisserman, A., 1993. An automated system for picking seismicevents. Expanded Abstr., 63rd Ann. Internat. SEG Mtg., Washington D.C.:234-237.
  34. Wang, Z., Ren, J., Zhang, D., Sun, M. and Jiang, J., 2018. A deep-learning based featurehybrid framework for spatiotemporal saliency detection inside videos.Neurocomput., 287: 68-83.
  35. Wang. W.. Gao, X. and Liu. X.W.. 2019. Applicable comparison among several firstarrival time automatic pick-up methods in tunnel advance detection by seismic wave.Tunnel Construct., 39: 1239-1246.
  36. Xiong, H.J., Guan, Y.P. and Yu, Y.J., 2009. Extraction of cophasal axes on seismicsections based on the edge detection method. Progr. Geophys. (in Chinese), 24:2250-2254.
  37. Yan, Y., Ren, J., Sun, G., Zhao, H., Han, J., Li, X., Marshall, S. and Zhan, J., 2018.
  38. Unsupervised image saliency detection with Gestalt-laws guided optimization andvisual attention based refinement, Pattern Recognit., 79: 65-78.
  39. Zhang, L.. Wan, C., Liu. H.. 2010. A method of Gabor filter direction selection using forpalmprint recognition. J. South-Central University for Nationalities, 29(4): 77-81.
  40. Zhao, H.. 2005. The laver tracking of fault’s sides based on the artificial neural networks.Chengdu University of Technology, Chengdu.
  41. Zhao, J., Ren, J.C., Gao, J.H., Tschannerl, J., Murray, P. and Wang, D., 2019. Automaticevents extraction in pre-stack seismic data based on edge detection in slant-stackedpeak amplitude profiles. J. Petrol. Sci. Engineer., 178: 459-466.
  42. Zhou, G.X. and Hu, Z.C., 1991. An AR-method for automatically tracking sync-phaseaxis of the seismic cross-section graph. Acta Automat. Sinica, 17(3): 4.mT
Share
Back to top
Journal of Seismic Exploration, Electronic ISSN: 0963-0651 Print ISSN: 0963-0651, Published by AccScience Publishing