Skip to main content

Research Repository

Advanced Search

Towards machine learning-driven practices for oil and gas decommissioning: introduction of a new offshore pipeline dataset.

Vuttipittayamongkol, Pattaramon; Tung, Aaron; Elyan, Eyad

Authors

Pattaramon Vuttipittayamongkol

Aaron Tung



Abstract

Thousands of offshore oil and gas structures worldwide are approaching the end of their operating lifespan. Decommissioning processes are expensive and normally take years to finish as various options need to be analysed based on numerous stakeholders' preferences. Despite recent and significant progress in machine learning and data-driven applications in the oil and gas industry, very little work has been done in the area of using machine learning to inform the decommissioning processes and operations. This can be attributed to the lack of relevant public datasets with sufficient samples. In this paper, we present a new oil and gas decommissioning dataset comprised of 708 real samples extracted from over a hundred company proposals and reports. A supervised learning algorithm was applied to the dataset to predict the decommissioning option. Experiments and results suggest that a machine learning approach can greatly help shorten the traditional analysis process while providing decent accuracy. The classification results of this work serve as a baseline to motivate further experiments and enable the research community to broaden and advance the knowledge in this prominent and timely topic.

Citation

VUTTIPITTAYAMONGKOL, P., TUNG, A. and ELYAN, E. 2021. Towards machine learning-driven practices for oil and gas decommissioning: introduction of a new offshore pipeline dataset. In Proceedings of the 9th International conference on computer and communications management (ICCCM 2021), 16-18 July 2021, [virtual event]. New York: ACM [online], pages 111-116. Available from: https://doi.org/10.1145/3479162.3479179

Conference Name 9th International conference on computer and communications management 2021 (ICCCM'21)
Conference Location [virtual event]
Start Date Jul 16, 2021
End Date Jul 18, 2021
Acceptance Date Jun 20, 2021
Online Publication Date Oct 28, 2021
Publication Date Dec 31, 2021
Deposit Date May 14, 2024
Publicly Available Date May 14, 2024
Publisher Association for Computing Machinery (ACM)
Pages 111-116
Series Title ACM International Conference Proceeding Series
ISBN 9781450390071
DOI https://doi.org/10.1145/3479162.3479179
Keywords Decision support solution; Decommissioning; Machine learning; Multi-criteria decision analysis tool; Offshore structures; Oil and gas; Stakeholder management
Public URL https://rgu-repository.worktribe.com/output/2057412

Files





You might also like



Downloadable Citations