Register      Login
Australian Energy Producers Journal Australian Energy Producers Journal Society
Journal of Australian Energy Producers
RESEARCH ARTICLE (Non peer reviewed)

Rapid play evaluation through AI interpretation

Jacob Smith A * and Peter Szafian B *
+ Author Affiliations
- Author Affiliations

A Geoteric, Perth, WA, Australia.

B Geoteric, London, UK.

* Correspondence to: jacob.smith@geoteric.com

The APPEA Journal 63 S275-S279 https://doi.org/10.1071/AJ22026
Accepted: 5 April 2023   Published: 11 May 2023

© 2023 The Author(s) (or their employer(s)). Published by CSIRO Publishing on behalf of APPEA.

Abstract

Recent years have brought an explosion in the application of advanced AI techniques to the imaging and interpretation of petroleum reservoirs. The ability of these techniques to image features in unprecedented detail, and within very short timeframes, has provided the opportunity for the industry to gain a more complete understanding of hydrocarbon reservoirs than ever before. The rapid evolution of these technologies has brought challenges however, as new workflows must be developed to gain the greatest value from these advancements. In this paper we look at the impact of these technologies on imaging, interpretation and modelling. This is done through an analysis of datasets spanning compressional and extensional systems, looking at both onshore and offshore data. A particular focus is given to recent acreage release areas. Through this analysis we find significant opportunities to revolutionise G&G workflows, but also unexpected challenges in understanding and integrating this newfound complexity. The given examples show that the interpreter is no longer working with the artificial simplicity of manually interpreted structures, but rather with a web of localised planes of slippage. Rather than the challenge of accurately identifying faults, we must focus on how to transfer this complexity into a useful interpretation and then into our static model. In these examples we can see that, through a reduction in manual processes, the interpreter can focus more of their energy on the iterative process of proposing and refining structural models, and that this process proves crucial to working effectively with these new methods.

Keywords: AI, artificial intelligence, automatic, faults, horizons, interpretation, planes, seismic, surfaces.

Jacob Smith is a member of the GeoTeric team, leading technical operations across the Asia Pacific Region. He received his BSc in Geophysics from Curtin University before starting his career in 2007. He has been with Geoteric since 2014, where he has been involved in projects across Australia, New Zealand, Japan, Papua New Guinea and South Korea. Jacob’s current focus is on developing workflows to take advantage of the novel AI Seismic Interpretation tools available within GeoTeric.

Peter Szafian has an MSc in Geophysics and a PhD in Earth Sciences. Peter has worked both in academia and in the oil industry. He joined Geoteric in 2013, where he is the Global Geosciences Manager. His primary responsibilities are workflow development and the technical oversight of the company’s geoscientists.


References

Amadi-Echendu J, Yakuba AE (2015) Asset operations: non-productive times during oil well drilling. In ‘Proceedings of the 7th World Congress on Engineering Asset Management (WCEAM 2012)’. (Eds W Lee, B Choi, L Ma, J Mathew) pp. 43–48. (Springer: Cham)
| Crossref |

Han C, Cader A (2020) Interpretational applications of artificial intelligence-based seismic fault delineation. First Break 38, 63–71.
Interpretational applications of artificial intelligence-based seismic fault delineation.Crossref | GoogleScholarGoogle Scholar |

Kranz B, Ormand C, Freeman B (2006) 3-D Structural Interpretation: Earth, Mind, and Machine. Vol. 111. (American Association of Petroleum Geologists Memoir)
| Crossref |

Lowell J, Erdogan V (2019) Combining artificial intelligence with human reasoning for seismic interpretation. In ‘SEG International Exposition and Annual Meeting’, September 2019, San Antonio, Texas, USA. (Society of Exploration Geophysicists)
| Crossref |

Marfurt KJ, Alves TM (2015) Pitfalls and limitations in seismic attribute interpretation of tectonic features. Interpretation 3, SB5–SB15.
Pitfalls and limitations in seismic attribute interpretation of tectonic features.Crossref | GoogleScholarGoogle Scholar |

Wu X, Shi Y, Fomel S, Luming L (2018) Convolutional Neural Networks for Fault Interpretation in Seismic Images. Paper presented at SEG International Exposition and Annual Meeting, Anaheim, California, USA, October 2018. (Society of Exploration Geophysicists) Available at https://doi.org/10.1190/segam2018‐2995341.1