Machine learning-based seismic characterization of deepwater turbidites in the Dangerous Grounds area, Northwest Sabah, offshore Malaysia

• Autorzy: Babikir Ismailalwali , Elsaadany Mohamed

Identyfikatory

DOI

10.1007/s11600-024-01396-2

• Języki publikacji: EN

Abstrakty

EN

Seismic interpretation is a critical aspect of hydrocarbon exploration, where geoscientists often struggle to accurately recognize patterns and anomalies in large datasets. Machine learning techniques offer a promising solution by allowing for the quick and accurate analysis of multiple and large-size seismic volumes. This study leverages seismic facies analysis, seismic attribute analysis, and supervised machine learning to identify and characterize turbidite deposits in the Dangerous Grounds region, an underexplored area recently revealed by high-resolution broadband seismic data. Through seismic stratigraphy, two distinct phases of turbidite deposition were identified: a lower unit showing higher amplitude and signs of faulting effect, and an upper, present-day unit characterized by lower amplitude and continuous reflectors. The attribute expression of these turbidites shows strong amplitude response, high relative acoustic impedance, and high gray-level co-occurrence matrix entropy emphasizing their distinctiveness from surrounding facies, with variations in reflector continuity and spectral decomposition providing further insight into their depositional processes and sediment characteristics. By applying nine machine learning classifiers with twenty seismic attributes as input, this study achieved over 99% accuracy in distinguishing turbidite facies from background, with the neural network, random forest, K-nearest neighbors, decision tree, and support vector machine exhibiting optimal performance. The study contributes significantly to the regional understanding of turbidite deposits through detailed machine learning-aided seismic characterization. It underscores the value of integrating domain knowledge with machine learning techniques in enhancing subsurface interpretations, offering a comprehensive methodology for seismic facies analysis in similarly complex and underexplored regions.

Słowa kluczowe

EN

Sabah; Malaysia; turbidites; seismic attributes; supervised machine learning; Dangerous Grounds; seismic facies classification

PL

Sabah; Malezja; turbidyty; atrybuty sejsmiczne; nadzorowane uczenie maszynowe

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2025
• Tom: Vol. 73, no. 1
• Strony: 379--391
• Opis fizyczny: Bibliogr. 38 poz.

Twórcy

autor

Babikir Ismailalwali

• Center for Subsurface Imaging, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia

• https://orcid.org/0000-0002-2333-3022

autor

Elsaadany Mohamed

• Center for Subsurface Imaging, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia

Bibliografia

• 1. Ali SH, Poppelreiter MC, Saw BB, Shah MM, Bashir Y (2021) Facies, diagenesis and secondary porosity of a Miocene reefal platform of Central Luconia. Malays Carbonates Evaporites 36:44
• 2. Babikir IAM, Salim AMA, Ghosh DP (2019) Lithogeomorphological facies analysis of upper miocene coal-prone fluviodeltaic reservoirs. Northern Malay Basin Interpret 7(3):T565-T579
• 3. Babikir I, Elsaadany M, Hermana M, Latiff AHA, Al-Masgari AA (2022b) Machine learning-aided seismic mapping of deepwater turbidites in the Dangerous Grounds region, offshore Northwest Sabah, Malaysia. Asia Petrol Geosci Conf Exhib (APGCE) 1:1-5
• 4. Babikir I, Elsaadany M, Sajid M, Laudon C (2022c) Evaluation of principal component analysis for reducing seismic attributes dimensions: implication for supervised seismic facies classification of a fluvial reservoir from the Malay Basin, offshore Malaysia. J Petrol Sci Eng 217(August):110911
• 5. Babikir I, Elsaadany M, Sajid M, Laudon C (2023) On the training sample size and classification performance: an experimental evaluation in seismic facies classification. Geoenergy Sci Eng 226:211809
• 6. Babikir I, Elsaadany M, Hermana M, Abdul Latiff AH, Al-Masgari AAS (2022) Attribute-assisted identification of carbonate seis- mic facies in the Dangerous Grounds region, Deepwater Sabah, Malaysia. 83rd EAGE Annual Conference & Exhibition
• 7. Banerjee A, Salim AMA (2021) Stratigraphic evolution of deepwater Dangerous Grounds in the South China Sea, NW Sabah plat¬form region, Malaysia. J Petrol Sci Eng 201:108434
• 8. Barnes AE (2007) Redundant and useless seismic attributes. Geo- physics 72(3):33-38
• 9. Bashir Y, Faisal MA, Biswas A, Babasafari AA, Ali SH, Imran QS, Siddiqui NA, Ehsan M (2021) Seismic expression of Miocene carbonate platform and reservoir characterization through geo- physical approach: application in Central Luconia, offshore Malaysia. Pet Explor Prod Technol 11:1533-1544
• 10. Berton F, Vesely FF (2016) Seismic expression of depositional elements associated with a strongly progradational shelf mar- gin: Northern Santos Basin, southeastern Brazil. Braz J Geol 46(4):585-603
• 11. Bishop C (2006) Pattern recognition and machine learning. Springer Brownlee J (2016) Machine learning algorithms from scratch with Python. Machine Learning Mastery
• 12. Chopra S, Marfurt KJ (2005) Seismic attributes—a historical perspective. Geophysics 70(5):3SO-28SO. https://doi.org/10.1190/1.2098670
• 13. Franke D, Barckhausen U, Baristeas N, Engels M, Ladage S, Lutz R, Montano J, Pellejera N (2011) The continent-ocean transition at the southeastern margin of the South China Sea. Mar Pet Geol 28(6):1187-1204
• 14. Franke D, Savva D, Pubellier M, Steuer S, Mouly B, Auxietre JL, Meresse F, Chamot-Rooke N (2014) The final rifting evolution in the South China Sea. Marine Pet Geol 58:704-720. https://doi.org/10.1016/j.marpetgeo.2013.11.020
• 15. Hinz K, Schluter HU (1985) Geology of the dangerous grounds, South China Sea, and the continental margin off Southwest Palawan: results of SONNE cruises SO-23 and SO-27. Energy 10(3-4):297-315
• 16. Hutchison CS, Vijayan VR (2010) What are the Spratly Islands? J Asian Earth Sci 39(5):371-385
• 17. Kim Y, Hardisty R, Marfurt KJ (2019) Attribute selection in seismic facies classification: application to a Gulf of Mexico 3D seismic survey and the Barnett Shale. Interpretation 7(3):1-54
• 18. Marfurt KJ (2018) Seismic attributes as the framework for data integration throughout the oilfield life cycle. Society of Exploration Geophysicists. https://doi.org/10.1190/1.9781560803522
• 19. McHargue T, Pyrcz MJ, Sullivan MD, Clark JD, Fildani A, Romans BW, Covault JA, Levy M, Posamentier HW, Drinkwater NJ (2011) Architecture of turbidite channel systems on the continental slope: patterns and predictions. Marine Pet Geol 28(3):728-743
• 20. Mitchum RM, Vail PR, Sangree JB (1977) Seismic stratigraphy and global changes of sea level, part 6: stratigraphic interpretation of seismic reflection patterns in depositional sequences. Seismi Stratigr Appl Hydrocarb Explor 165:117-134
• 21. Mutti E, Normark WR (1991) An integrated approach to the study of turbidite systems. In: Weimer P, Link MH (eds) Seismic facies and sedimentary processes of submarine fans and turbidite systems. Springer, New York, pp 75-106. https://doi.org/10.1007/ 978-1-4684-8276-8_4
• 22. Normark WR, Posamentier H, Mutti E (1993) Turbidite systems: state of the art and future directions. Rev Geophys 93:91-116
• 23. Peng X, Shen C, Mei L, Zhao Z, Xie X (2019) Rift-drift transition in the Dangerous Grounds. South China Sea Mar Geophys Res 40(2):163-183
• 24. Posamentier HW (2004) Seismic geomorphology: imaging elements of depositional systems from shelf to deep basin using 3D seis- mic data: implications for exploration and development. Geol Soc London Mem 29(1):11-24. https://doi.org/10.1144/GSL.MEM. 2004.029.01.02
• 25. Posamentier HW, Kolla V (2003) Seismic geomorphology and stratigraphy of depositional elements in deepwater settings. J Sediment Res 73(3):367-388
• 26. Posamentier HW, Paumard V, Lang SC (2022) Principles of seismic stratigraphy and seismic geomorphology I: extracting geologic insights from seismic data. Earth Sci Rev 228:103963
• 27. Roden R, Smith T, Sacrey D (2015) Geologic pattern recognition from seismic attributes: principal component analysis and self-organizing maps. Interpretation 3(4):SAE59-SAE83. https://doi.org/10.1190/INT-2015-0037.1
• 28. Steuer S, Franke D, Meresse F, Savva D, Pubellier M, Auxietre JL (2014) Oligocene-Miocene carbonates and their role for con- straining the rifting and collision history of the dangerous grounds, South China Sea. Mar Pet Geol 58:644-657. https://doi. org/10.1016/j.marpetgeo.2013.12.010
• 29. Stow D, Smillie Z (2020) Distinguishing between deep-water sediment facies: turbidites, contourites and hemipelagites. Geosciences 10(2):68. https://doi.org/10.3390/geosciences10020068
• 30. Su-Mei H, Zhao-Hui S, Meng-Ke Z, San-Yi Y, Shang-Xu W (2022) Incremental semi-supervised learning for intelligent seismic facies identification. Appl Geophys 19:41-52
• 31. Wang Y, Zhao Y, Ding W, Fang P, Li J (2022) Cenozoic propagated rifting in the Dangerous Grounds in response to the epi- sodic seafloor spreading of the South China Sea. J Earth Sci 33(4):1031-1046
• 32. Wang Q, Wang Z, Gao D, Gao Z, Jia J, Zhu J, Gao J (2023) Seismic attribute analysis with a combination of convolutional autoencoder and random forest in a turbidite reservoir. Geophysics 89(1):WA207-WA217. https://doi.org/10.1190/geo2023-0127.1
• 33. Witten IH (2011) Data mining: practical machine learning tools and techniques. Elsevier, Amsterdam
• 34. Wrona T, Pan I, Gawthorpe RL, Fossen H (2018) Seismic facies analysis using machine learning. Geophysics 83(5):083-095
• 35. Xu G, Haq BU (2022) Seismic facies analysis: past, present and future. Earth Sci Rev 224:103876
• 36. Zeng H (2018) What is seismic sedimentology? A tutorial. Interpretation 6(2):SD1-SD12. https://doi.org/10.1190/INT-2017-0145.1
• 37. Zhao T, Jayaram V, Roy A, Marfurt KJ (2015) A comparison of classification techniques for seismic facies recognition. Interpretation 3(4):SAE29-SAE58. https://doi.org/10.1190/INT-2015-0044.1
• 38. Zhao T, Zhang J, Li F, Marfurt KJ (2016) Characterizing a turbidite system in Canterbury Basin, New Zealand, using seismic attributes and distance-preserving self-organizing maps. Interpretation 4(1):SB79-SB89. https://doi.org/10.1190/INT-2015-0094.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).