Application of a Pre-Trained CNN Model for Fault Interpretation in the Structurally Complex Browse Basin, Australia
Source abstract
Abstract
Fault detection is an important step in subsurface interpretation and reservoir characterization from 3D seismic images. Due to the numerous and complex fault structures in seismic images, manual seismic interpretation is time-consuming and requires intensive work. We applied a pre-trained CNN model to predict faults from the 3D seismic volume of the Poseidon field in the Browse Basin, Australia. This field is highly structured with complex normal faulting throughout the targeted Plover Formations. Our motivation for this work is to compare machine-learning-based fault prediction to user-interpreted fault identification supported by seismic variance attributes. We found reasonably satisfactory results using CNN with an improved fault probability volume that outperforms variance technology. Therefore, we propose that this workflow could reduce time and be able to predict faults quite accurately in most structurally complex areas.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Seismic Imaging and Inversion Techniques · Drilling and Well Engineering · Hydraulic Fracturing and Reservoir Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Centre for Subsurface Imaging, Department of Geosciences, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, Tronoh 32610, Malaysia
Funding
Machine Learning Application in lithology and fluid properties Prediction utilizing seismic and well log data for optimal reservoir characterization
References (46)
Show source-provided references
1. T Multi-attribute ant-tracking and neural network for fault detection: A case study of an Iranian oilfield10.1088/1742-2132/10/1/015009 ↗
2. Seismic fault detection in real data using transfer learning from a convolutional neural network pre-trained with synthetic seismic data10.1016/j.cageo.2019.104344 ↗
3. Di, H., Wang, Z., and AlRegib, G. (2018). Seismic Fault Detection from Post-Stack Amplitude by Convolutional Neural Networks, European Association of Geoscientists & Engineers.10.3997/2214-4609.201800733 ↗
4. Improving seismic fault mapping through data conditioning using a pre-trained deep convolutional neural network: A case study on Groningen field10.1016/j.petrol.2022.110411 ↗
5. Uncertainty in structural interpretation: Lessons to be learnt10.1016/j.jsg.2015.03.003 ↗
6. Impact of seismic image quality on fault interpretation uncertainty
7. Seismic attributes in reservoir characterization: An overview10.1007/s12517-021-06626-1 ↗
8. Fault Enhancement in Seismic Images by Introducing a Novel Strategy Integrating Attributes and Image Analysis Techniques10.1007/s00024-022-03014-y ↗
9. Boe, T.H., and Daber, R. (2010). SEG Technical Program Expanded Abstracts 2010, Society of Exploration.
10. Yan, Z., Zhang, Z., and Liu, S. (2021). Improving Performance of Seismic Fault Detection by Fine-Tuning the Convolutional Neural Net-work Pre-Trained with Synthetic Samples. Energies, 14.10.3390/en14123650 ↗
11. 3-D Seismic Fault Detection Using Recurrent Convolutional Neural Networks with Com-pound Loss10.1109/TGRS.2023.3275951 ↗
12. Seismic attribute assisted analysis of the interpretational variations in the time and depth migrated datasets: An example from Taranaki Basin, New Zealand10.1016/j.marpetgeo.2023.106301 ↗
13. 3-D seismic attributes using a semblance-based coherency algorithm10.1190/1.1444415 ↗
14. Seismic fault detection using convolutional neural networks with focal loss10.1016/j.cageo.2021.104968 ↗
15. Multidirectional Coherence Attribute for Discontinuity Characterization in Seismic Images10.1109/LGRS.2022.3151686 ↗
16. Seismic Coherence Attribute Based on Eigenvectors and Its Application10.1109/LGRS.2023.3296835 ↗
17. Directional complex-valued coherence attributes for discontinuous edge detection10.1016/j.jappgeo.2016.03.016 ↗
18. Fault enhancement comparison among coherence enhancement, probabilistic neural net-works, and convolutional neural networks in the Taranaki Basin area, New Zealand10.1190/INT-2021-0151.1 ↗
19. Ashraf, U., Zhang, H., Anees, A., Nasir Mangi, H., Ali, M., Ullah, Z., and Zhang, X. (2020). Application of Unconventional Seismic Attrib-utes and Unsupervised Machine Learning for the Identification of Fault and Fracture Network. Appl. Sci., 10.10.3390/app10113864 ↗
20. Methods to compute fault images, extract fault surfaces, and estimate fault throws from 3D seismic images10.1190/geo2012-0331.1 ↗
21. Imran, Q.S., Siddiqui, N.A., Latiff, A.H.A., Bashir, Y., Khan, M., Qureshi, K., Al-Masgari, A.A.-S., Ahmed, N., and Jamil, M. (2021). Automated fault detection and extraction under gas chimneys using hybrid discontinuity attributes. Appl. Sci., 11.10.3390/app11167218 ↗
22. Kim, M., Yu, J., Kang, N.-K., and Kim, B.-Y. (2021). Improved Workflow for Fault Detection and Extraction Using Seismic Attributes and Orientation Clustering. Appl. Sci., 11.10.3390/app11188734 ↗
23. A buried hill fault detection method based on 3D U-SegNet and transfer learning10.1016/j.petrol.2022.110917 ↗
24. 3D seismic flexure analysis for subsurface fault detection and fracture characterization10.1007/s00024-016-1406-9 ↗
25. Qi, X., and Marfurt, K. (2017, January 24–29). Volumetric aberrancy to map subtle faults and flexures. Proceedings of the 2017 SEG International Exposition and Annual Meeting, Houston, TX, USA.10.1190/segam2017-17632807.1 ↗
26. Aqrawi, A.A., and Boe, T.H. (2011). SEG Technical Program Expanded Abstracts 2011: Society of Exploration Geophysicists, Society of Exploration.
27. Seismic attribute selection for machine-learning-based facies analysis10.1190/geo2019-0223.1 ↗
28. Seismic Coherence for Discontinuity Interpretation10.1007/s10712-021-09670-4 ↗
29. Gray-level transformation and Canny edge detection for 3D seismic discontinuity enhancement10.1016/j.cageo.2014.07.011 ↗
30. Attribute extraction: An important application in any detailed 3-D interpretation study10.1190/1.1436837 ↗
31. 3D reflection seismic imaging of natural gas/fluid escape features in the dee[1]p-water Orange Basin of South Africa10.1007/s11001-023-09523-2 ↗
32. Semiautomated fault interpretation based on seismic attributes10.1190/INT-2013-0060.1 ↗
33. Display and enhancement of volumetric fault images10.1190/INT-2015-0104.1 ↗
34. Di, H., Shafiq, M.A., and AlRegib, G. (2017, January 24–29). Seismic-fault detection based on multiattribute support vector machine analysis. Proceedings of the 2017 SEG International Exposition and Annual Meeting, Houston, TX, USA.10.1190/segam2017-17748277.1 ↗
35. Di, H., Shafiq, M., and AlRegib, G. (2018). SEG Technical Program Expanded Abstracts 2018: Society of Exploration Geophysicists, Society of Exploration.
36. A comparison of classification techniques for seismic facies recognition10.1190/INT-2015-0044.1 ↗
37. Struckmeyer, H.I., Blevin, J.E., Sayers, J., Totterdell, J.M., Baxter, K., and Cathro, D.L. (1998). Structural Evolution of the Browse Basin, Northwest Shelf: New Concepts from Deep-Seismic Data, PESA.
38. Patadiya, P., Parmar, J., Ramalingam, V., and Singh, A. (2023). Hydrocarbon Source Rock Characterization and Basin Modelling, A Case Study from Poseidon Field, Browse Basin, Australia, European Association of Geoscientists & Engineers.10.3997/2214-4609.2023101452 ↗
39. Detection of gas chimney and its linkage with deep-seated reservoir in poseidon, NW shelf, Australia from 3D seismic data using multi-attribute analysis and artificial neural network approach10.1016/j.jngse.2020.103586 ↗
40. Seismic attributes for hydrocarbon detection and reservoir characterization: A case study from Poseidon field, Northwestern Australia10.1007/s12517-021-08853-y ↗
41. Hoffman, N., Hill, K., Ellis, G., Baillie, P., and Munson, T. (2003, January 19–20). Structural-stratigraphic evolution and hydrocarbon prospectivity of the deep-water Browse Basin, Northwest Shelf, Australia. Proceedings of the Timor Sea Symposium, Timor Sea Petroleum Geoscience, Darwin, Australia.
42. Farfour, M., and Foster, D. (September, January 28). Machine learning and seismic attributes for prospect identification and risking: An example from offshore Australia. Proceedings of the SEG/AAPG International Meeting for Applied Geoscience & Energy, Houston, TX, USA.
43. Le Poidevin, S.R., Temple, P., Edwards, D.S., and Kuske, T. (2015). Australian Petroleum Accumulations Report 7 Browse Basin: Western Australia and Territory of Ashmore and Cartier Islands Adjacent Area.10.11636/Record.2015.010 ↗
44. Improving seismic fault detection by super-attribute-based classification10.1190/INT-2018-0054.1 ↗
45. Fast structural interpretation with structure-oriented filtering10.1190/1.1598121 ↗
46. An enhanced fault detection workflow combining machine learning and seismic attributes yields an improved fault model for Caspian Sea asset10.3997/1365-2397.fb2021075 ↗