Integration of feature extraction, attribute combination and image segmentation for object delineation on seismic images

• Autorzy: Khayer Keyvan , Hosseini Fard Esmail , Roshandel Kahoo Amin , Soleimani Monfared Mehrdad , Ahmadyfard Alireza

Identyfikatory

DOI

10.1007/s11600-022-00921-5

• Języki publikacji: EN

Abstrakty

EN

Automatic geological interpretation, specifically modeling salt dome and fault detection, is controversial task on seismic images from complex geological media. In advanced techniques of seismic interpretation and modeling, various strategies are utilized for combination and integration different information layers to obtain an image adequate for automatic extraction of the object from seismic data. Efficiency of the selected feature extraction, data integration and image segmentation methods are the most important parameters that affect accuracy of the final model. Moreover, quality of the seismic data also affects confidence of the selected seismic attributes for integration. The present study proposed a new strategy for efficient delineation and modeling of geological objects on the seismic image. The proposed method consists of extraction specific features by the histogram of oriented gradients (HOG) method, statistical analysis of the HOG features, integration of features through hybrid attribute analysis and image classification or segmentation. The final result is a binary model of the target under investigation. The HOG method here modified accordingly for extraction of the related features for delineation of salt dome and fault zones from seismic data. The extracted HOG parameter then is statically analyzed to define the best state of information integration. The integrated image, which is the hybrid attribute, then is used for image classification, or image segmentation by the image segmentation method. The seismic image labeling procedure performs on the related seismic attributes, evaluated by the extracted HOG feature. Number of HOG feature and the analyzing parameters are also accordingly optimized. The final image classification then is performed on an image which contains all the embedded information on all the related textural conventional and statistical attributes and features. The proposed methods here apply on four seis mic data examples, synthetic model of salt dome and faults and two real data that contain salt dome and fault. Results have shown that the proposed method can more accurately model the targets under investigation, compared to advanced extracted attributes and manual interpretations.

Słowa kluczowe

EN

seismic interpretation; feature extraction; image segmentation; attribute integration; HOG

PL

interpretacja sejsmiczna; ekstrakcja cech; segmentacja obrazu

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2023
• Tom: Vol. 71, no. 1
• Strony: 275--292
• Opis fizyczny: Bibliogr. 56 poz.

Twórcy

autor

Khayer Keyvan

• Department of Mining, Petroleum and Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran

• https://orcid.org/0000-0002-7613-1707

autor

Hosseini Fard Esmail

• Department of Mining, Petroleum and Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran

autor

Roshandel Kahoo Amin

• Department of Mining, Petroleum and Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran

• https://orcid.org/0000-0002-2214-2558

autor

Soleimani Monfared Mehrdad

• Department of Mining, Petroleum and Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran
• Geophysical Institute (GPI), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany

• https://orcid.org/0000-0003-4755-4214

autor

Ahmadyfard Alireza

• Department of Electrical and Robotic Engineering, Shahrood University of Technology, Shahrood, Iran

Bibliografia

• 1. Aggarwal JK, Xia L (2014) Human activity recognition from 3D data: a review. Pattern Recogn Lett 48:70–80. https://doi.org/10.1016/j.patrec.2014.04.011
• 2. Ahmed S, Gillian M, Fiona CD, Rebecca MR, Scott IS, James PB (2017) Histograms of oriented 3D gradients for fully automated fetal brain localization and robust motion correction in 3 T magnetic resonance images. BioMed Res Int. ID 3956363. https://doi.org/10.1155/2017/3956363
• 3. Amin A, Deriche M (2015) A new approach for salt dome detection using a 3D multidirectional edge detector. Appl Geophys 12(3):334–342. https://doi.org/10.1007/s11770-015-0512-2
• 4. Amin A, Deriched M (2016) Salt-dome detection using a codebook-based learning model. IEEE Geosci Remote Sens Lett 13(11):1636–1640. https://doi.org/10.1109/LGRS.2016.2599435
• 5. Amin A, Deriche M, Hegazy T, Wang Z, AlRegib G (2015) A novel approach for salt dome detection using a dictionary-based classifier. In: SEG technical program expanded abstracts. Soc Exploration Geophysicists, pp 1816–1820. https://doi.org/10.1190/segam2015-5925748.1
• 6. Amin A, Deriche M, Shafiq MA, Wang Z, AlRegib G (2017) Automated salt-dome detection using an attribute ranking framework with a dictionary-based classifier. Interpretation 5(3):SJ61–SJ79. https://doi.org/10.1190/INT-2016-0084.1
• 7. Aqrawi AA, Boe TH (2011) Improved fault segmentation using a dip guided and modified 3D Sobel filter. In: SEG Technical Program Expanded Abstracts 2011 (pp. 999–1003). Society of Exploration Geophysicists. https://doi.org/10.1190/1.3628241
• 8. Bahorich M, Farmer S (1995) 3-D seismic discontinuity for faults and stratigraphic features: the coherence cube. Lead Edge 14(10):1053–1058
• 9. Berthelot A, Solberg AH, Morisbak E, Gelius LJ (2011) Salt diapirs without well defined boundaries—a feasibility study of semi-automatic detection. Geophys Prospect 59:682–696. https://doi.org/10.1111/j.1365-2478.2011.00950.x
• 10. Berthelot A, Solberg AH, Gelius LJ (2013) Texture attributes for detection of salt. J Appl Geophys 88:52–69. https://doi.org/10.1016/j.jappgeo.2012.09.006
• 11. Boe TH, Daber R (2010) Seismic features and the human eye: RGB blending of azimuthal curvatures for enhancement of fault and fracture interpretation. In SEG Technical Program Expanded Abstracts 2010 (pp. 1535–1539). Society of Exploration Geophysicists. https://doi.org/10.1190/1.3513133
• 12. Chen Y (2017) Automatic microseismic event picking via unsupervised machine learning. Geophys J Int 212:88–102. https://doi.org/10.1093/gji/ggx420
• 13. Chen Y, Huang W, Zhang D, Chen W (2016) An open-source matlab code package for improved rank-reduction 3D seismic data denoising and reconstruction. Comput Geosci 95:59–66. https://doi.org/10.1016/j.cageo.2016.06.017
• 14. Chen Y, Zhang G, Bai M, Zu S, Guan Z, Zhang M (2019) Automatic waveform classification and arrival picking based on convolutional neural network. Earth and Space Science 6:1244–1261. https://doi.org/10.1029/2018EA000466
• 15. Di H, AlRegib G (2020) A comparison of seismic saltbody interpretation via neural networks at sample and pattern levels. Geophys Prospect 68(2):521–535. https://doi.org/10.1111/1365-2478.12865
• 16. Di H, Gao D, AlRegib G (2018) 3D structural-orientation vector guided auto tracking for weak seismic reflections: a new tool for shale reservoir visualization and interpretation. Interpretation 6:SN47-SN56. https://doi.org/10.1190/INT-2018-0053.1
• 17. Farrokhnia F, Kahoo AR, Soleimani M (2018) Automatic salt dome detection in seismic data by combination of attribute analysis on CRS images and IGU map delineation. J Appl Geophys 159:395–407. https://doi.org/10.1016/j.jappgeo.2018.09.018
• 18. Glinskii BM, Sobisevich AL, Fat’yanov AG, Khairetdinov MS (2008) Mathematical simulation and experimental studies of the shugo mud volcano. J Volcanol Seismolog 2:364–371. https://doi.org/10.1134/S0742046308050060
• 19. Guitton A, Wang H, Trainor-Guitton W (2017) Statistical imaging of faults in 3D seismic volumes using a machine learning approach. SEG Technical Program Expanded Abstracts. https://doi.org/10.1190/segam2017-17589633.1
• 20. Guo B, Li L, Luo Y (2018) A new method for automatic seismic fault detection using convolutional neural network. In SEG Technical Program Expanded Abstracts 2018 (pp. 1951–1955). Society of Exploration Geophysicists. https://doi.org/10.1190/segam2018-2995894.1
• 21. Halpert AD, Clapp RG, Biondi B (2014) Salt delineation via interpreter-guided 3D seismic image segmentation. Interpretation 2(2):T79–T88. https://doi.org/10.1190/INT-2013-0159.1
• 22. Hegazy T, AlRegib G (2014) Texture attributes for detecting salt bodies in seismic data. In: SEG Technical Program Expanded Abstracts. Society of Exploration Geophysicists, pp 1455–1459. https://doi.org/10.1190/segam2014-1512.1
• 23. Hosseini-Fard E, Roshandel-Kahoo A, Soleimani-Monfared M, Khayer K, Ahmadi-Fard AR (2022) Automatic seismic image segmentation by introducing a novel strategy in histogram of oriented gradients. J Petrol Sci Eng 209:109971. https://doi.org/10.1016/j.petrol.2021.109971
• 24. Kumar PC, Mandal A (2018) Enhancement of fault interpretation using multi-attribute analysis and artificial neural network (ANN) approach: a case study from Taranaki Basin, New Zealand. Explor Geophys 49:409–424. https://doi.org/10.1071/EG16072
• 25. Kumar PC, Sain K (2018) Attribute amalgamation-aiding interpretation of faults from seismic data: an example from Waitara 3D prospect in Taranaki basin off New Zealand. J Appl Geophys 159:52–68. https://doi.org/10.1016/j.jappgeo.2018.07.023
• 26. Lobos R, Silva JF, Ortiz JM, Díaz G, Egaña A (2016) Analysis and classification of natural rock textures based on new transform-based features. Math Geosci 48:835–870. https://doi.org/10.1007/s11004-016-9648-8
• 27. Maestrelli D, Iacopini D, Jihad AA, Bond CE, Bonini M (2017) Seismic and structural characterization of fluid escape pipes using 3D and partial stack seismic from the Loyal Field, A multiphase and repeated intrusive mechanism. Mar Petrol Geol 88:489–510. https://doi.org/10.1016/J.MARPETGEO.2017.08.016
• 28. Mauri G, Husein A, Mazzini A, Irawan D, Sohrabi R, Hadi S, Prasetyo H, Miller SA (2017) Insights on the structure of Lusi mud edifice from land gravity data. Mar Pet Geol 90:104–115. https://doi.org/10.1016/j.marpetgeo.2017.05.041
• 29. Mousavi J, Radad M, Soleimani Monfared M, Roshandel Kahoo A (2022) Fault enhancement in seismic images by introducing a novel strategy integrating attributes and image analysis techniques. Pure Appl Geophys, 1–16. https://doi.org/10.1007/s00024-022-03014-y
• 30. Naseer MT (2020) Seismic attributes and reservoir simulation’ application to image the shallow-marine reservoirs of Middle-Eocene carbonates, SW Pakistan. J Petrol Sci Eng 195:107711. https://doi.org/10.1016/j.petrol.2020.107711
• 31. Qu S, Guan Z, Verschuur E, Chen Y (2019) Automatic high-resolution microseismic event detection via supervised machine learning. Geophys J Int 218(3):2106–2121. https://doi.org/10.1093/gji/ggz273
• 32. Radfar A, Rahimi A, Nejati A, Soleimani M, Taati F (2018) New insights into the structure of the South Caspian Basin from seismic reflection data, Gorgan Plain. Iran Int J Earth Sci 108:379–402. https://doi.org/10.1007/s00531-018-1659-x
• 33. Roberts A (2001) Curvature attributes and their application to 3 D interpreted horizons. First Break 19(2):85–100
• 34. Shafiq MA, Wang Z, Amin A, Hegazy T, Deriche M, AlRegib H (2015) Detection of salt-dome boundary surfaces in migrated seismic volumes using gradient of textures. SEG Technical Program Expanded Abstracts 1811–1815. https://doi.org/10.1190/segam2015-5927230.1
• 35. Shafiq MA, Wang Z, AlRegib G, Amin A, Deriche M (2017) A texture-based interpretation workflow with application to delineating salt domes. Interpretation 5:SJ1–SJ19. https://doi.org/10.1190/INT-2016-0043.1
• 36. Shafiq MA, Di H, AlRegib G (2018) A novel approach for automated detection of listric faults within migrated seismic volumes. J Appl Geophys 155:94–101. https://doi.org/10.1016/j.jappgeo.2018.05.013
• 37. Shahbazi A, Ghosh D, Soleimani M, Gerami A (2016) Seismic imaging of complex structures with the CO-CDS stack method. Stud Geophys Geod 60(4):662–678. https://doi.org/10.1007/s11200-015-0452-6
• 38. Shahbazi A, Soleimani M, Thiruchelvam V, Fei TK, Babasafari AA (2020) Integration of knowledge-based seismic inversion and sedimentological investigations for heterogeneous reservoir. J Asian Earth Sci 202:104541. https://doi.org/10.1016/j.jseaes.2020.104541
• 39. Shu C, Ding X, Fang C (2011) Histogram of the oriented gradient for face recognition. Tsinghua Sci Technol 16:216–224. https://doi.org/10.1016/S1007-0214(11)70032-3
• 40. Singh D, Kumar PC, Sain K (2016) Interpretation of gas chimney from seismic data using artificial neural network: a study from Maari 3D prospect in the Taranaki basin, New Zealand. J Natural Gas Science Eng 36:339–357. https://doi.org/10.1016/j.jngse.2016.10.039
• 41. Soleimani M (2016a) Seismic image enhancement of mud volcano bearing complex structure by the CDS method, a case study in SE of the Caspian Sea shoreline. Russ Geol Geophys 57:1757–1768. https://doi.org/10.1016/j.rgg.2016.01.020
• 42. Soleimani M (2016b) Seismic imaging by 3D partial CDS method in complex media. J Petrol Sci Eng 143:54–64. https://doi.org/10.1016/j.petrol.2016.02.019
• 43. Soleimani M, Rafie M (2016) Imaging of seismic data in complex structures by introducing the partial diffraction surface stack method. Stud Geophys Geod 60. https://doi.org/10.1007/s11200-015-0942-6
• 44. Soleimani M, Shokri BJ (2015) 3D static reservoir modeling by geostatistical techniques used for reservoir characterization and data integration. Environ Earth Sci 74:1403–1414. https://doi.org/10.1007/s12665-015-4130-3
• 45. Soleimani M, Aghajani H, Heydari-Nejad S (2018a) Structure of giant buried mud volcanoes in the South Caspian Basin: Enhanced seismic image and field gravity data by using normalized full gradient method. Interpretation 6:T861–T872. https://doi.org/10.1190/INT-2018-0009.1
• 46. Soleimani M, Aghajani H, Heydari-Nejad S (2018b) Salt dome boundary detection in seismic image via resolution enhancement by the improved NFG method. Acta Geod Geoph 53:463–478. https://doi.org/10.1007/s40328-018-0222-3
• 47. Soltani P, Soleimani M, Aghajani H (2017) Faults and fractures detection in 2D seismic data based on principal component analysis. Int J Mining Geo-Eng 51(2):199–207. https://doi.org/10.22059/ijmge.2017.212587.594618
• 48. Somoza L, Medialdea T, León R, Ercilla G, Vázquez JT, líFarran M, Hernández-Molina J, González J, Juan J, Fernández-Puga MC (2012) Structure of mud volcano systems and pockmarks in the region of the Ceuta Contourite Depositional System (Western Alborán Sea). Mar Geol 332:4–26. https://doi.org/10.1016/j.margeo.2012.06.002
• 49. Tingdahl KM, De Rooij M (2005) Semi-automatic detection of faults in 3D seismic data. Geophys Prospect 53(4):533–542
• 50. Torrione PA, Morton KD, Sakaguchi R, Collins LM (2014) Histograms of oriented gradients for landmine detection in ground-penetrating radar data. IEEE Trans Geosci Remote Sens 52:1539–1550. https://doi.org/10.1109/TGRS.2013.2252016
• 51. Vajda S, Karargyris A, Jaeger S, Santosh KC, Candemir S, Xue Z, Antani S, Thoma G (2018) Feature selection for automatic tuberculosis screening in frontal chest radiographs. J Med Syst 42(8):146. https://doi.org/10.1007/s10916-018-0991-9
• 52. Van Gent H, Urai JL, de Keijzer M (2011) The internal geometry of salt structures e A first look using 3D seismic data from the Zechstein of the Netherlands. J Struct Geol 33:292–311. https://doi.org/10.1016/j.jsg.2010.07.005
• 53. Velidou DS, Tolpekin VA, Stein A, Woldai T (2015) Use of gestalt theory and random sets for automatic detection of linear geological features. Math Geosci 47:249–276. https://doi.org/10.1007/s11004-015-9584-z
• 54. Xing J, Spiess V (2015) Shallow gas transport and reservoirs in the vicinity of deeply rooted mud volcanoes in the central Black Sea. Mar Geol 369:67–78. https://doi.org/10.1016/j.margeo.2015.08.005
• 55. Zhang G, Wang Z, Chen Y (2018) Deep learning for seismic lithology prediction. Geophys J Int 215:1368–1387. https://doi.org/10.1093/gji/ggy344
• 56. Zheng ZH, Kavousi P, Di HB (2014) Multi-attributes and neural network-based fault detection in 3D seismic interpretation. Adv Mater Res 838:1497–1502. https://doi.org/10.4028/www.scientific.net/AMR.838-841.1497

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).