Applying Machine Learning to the Fuel Theft Problem on Pipelines
Publication: Journal of Pipeline Systems Engineering and Practice
Volume 14, Issue 2
Abstract
Fuel theft of oil pipelines is a concern faced by various countries and oil and gas companies due to its impact on the environment and the safety of neighboring communities. Oil pipeline monitoring and inspection with the support of alerts is essential to preventing suspected fuel-theft events and mitigating risks. Monitoring systems trigger alerts, and patrols are sent to confirm the occurrence of illegal tapping. However, various signals can be activated briefly, and the correct prioritization is essential to identifying illegal tapping as quickly as possible. This work aims to use machine-learning techniques to develop a predictive model capable of forecasting the probability of an event resulting in illegal tapping and understanding the factors that influence the occurrence. A Brazilian oil and gas transportation company provided data from a monitoring system supervised from January 2019 to August 2021. Five machine-learning algorithms were used in this study: Logistic Regression, Random Forest, XGBoost, Catboost, and Multilayer Perceptron. The Random Forest obtained the best results in classifying alerts associated (or not) with an illegal tapping, showing accuracy, specificity, and sensitivities of 76.8%, 68.3%, and 100%, respectively. In this problem, specificity implies reducing the sending of patrols to the field in 68.3% of circumstances, and sensitivity means that the model is a good predictor for positive cases. As for the external validation, the model also performed well, with an accuracy and specificity of 61%. The factors that most highly influenced illegal tapping occurrences were the alert duration, previous events in the same area, and events during the night.
Practical Applications
The problem of fuel theft of oil pipelines affects several countries worldwide and is a major concern due to its impact on the environment and the safety of neighboring communities. Oil pipeline surveillance through monitoring systems is important to prevent suspected fuel-theft events and mitigate risks. However, many alerts can be triggered in a brief period, and their correct prioritization is essential to identifying illegal tapping as quickly as possible. This work used machine-learning techniques to develop a predictive model capable of forecasting the probability of an event resulting in illegal tapping. Moreover, it has identified the factors that most influence a fuel-theft occurrence: alert duration, previous events in the same area, and the night period. The developed model can be used to assist companies in prioritizing alerts and improving the efficiency of patrol responses, contributing to combat, and reducing fuel theft.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are proprietary or confidential in nature and may only be provided with restrictions.
Acknowledgments
We want to thank all collaborators from Transpetro, who specified and developed the project and provided data. This study was supported by the Coordination for the Improvement of Higher Education Personnel (CAPES)—Finance Code 001, the Carlos Chagas Filho Foundation for Research Support of the State of Rio de Janeiro (FAPERJ), the Brazilian National Council for Scientific and Technological Development (CNPq), and by departmental funds from Transpetro.
Author Contributions: SH, LFD, and MVBR contributed to the study conception and design, besides data interpretation. RMV, LFD, and BB performed data processing, statistical analysis, and model development. RMV, LFD, BB, and SH drafted the first version of the manuscript. SH, MVBR, ASD, and FCR supervised the study. ASD and FCR contributed equally. All authors had full access to data, participated in data interpretation, revised the manuscript, and approved the final version of the manuscript.
References
Akinsete, O., and A. Oshingbesan. 2019. “Leak detection in natural gas pipelines using intelligent models.” In Proc., SPE Nigeria Annual Int. Conf. and Exhibition. Calgary, AB, Canada: Society of Petroleum Engineers.
Anifowose, B., D. M. Lawler, D. Horst, and L. Chapman. 2012. “Attacks on oil transport pipelines in Nigeria: A quantitative exploration and possible explanation of observed patterns.” Appl. Geogr. 32 (2): 636–651. https://doi.org/10.1016/j.apgeog.2011.07.012.
ANP (Agência Nacional de Petróleo, Gás Natural e Biocombustíveis). 2020. “Anuário Estatístico Brasileiro do Petróleo, Gás Natural e Biocombustíveis.” Accessed July 6, 2021. https://www.gov.br/anp/pt-br/centrais-de-conteudo/publicacoes/anuario-estatistico/anuario-estatistico-2021.
Araujo, M. S., H. A. Spidle, S. P. Siebenaler, S. G. Blaisdell, and D. W. Vickers. 2018. “Application of machine learning to distributed temperature sensing (DTS) systems.” In Proc., 2018 12th Int. Pipeline Conf. Volume 3: Operations, Monitoring, and Maintenance; Materials and Joining. Calgary, AB: ASME.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (4): 5–32. https://doi.org/10.1023/A:1010933404324.
Chen, T., and C. Guestrin. 2016. “XGBoost.” In Proc., 22nd Acm Sigkdd Int. Conf. on Knowledge Discovery and Data Mining, 785–794. London: ACM.
Cruz, R. P., F. V. Silva, and A. M. F. Fileti. 2020. “Machine learning and acoustic method applied to leak detection and location in low-pressure gas pipelines.” Clean Technol. Environ. Policy 22 (3): 627–638. https://doi.org/10.1007/s10098-019-01805-x.
Dantas, L. 2020. “Predicting the acquisition of resistant pathogens in ICUs using machine learning techniques.” Ph.D. thesis, Dept. of Industrial Engineering, Pontifical Catholic Univ. of Rio de Janeiro.
Exaudi, K., R. Passarella, R. Rendyansyah, and R. Zulfahmi. 2018. “Using pressure sensors towards pipeline leakage detection.” In Proc., 2018 Int. Conf. on Electrical Engineering and Computer Science (ICECOS), 89–92. New York: IEEE.
Galar, M., A. Fernandez, E. Barrenechea, H. Bustince, and F. Herrera. 2012. “A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches.” IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 42 (4): 463–484. https://doi.org/10.1109/TSMCC.2011.2161285.
GFI (Global Financial Integrity). 2017. “Transnational crime and the developing world.” Accessed July 6, 2021. http://www.gfintegrity.org/wp-content/uploads/2017/03/Transnational_Crime-final.pdf.
Han, J., M. Kamber, and J. Pei. 2011. Data mining: Concepts and techniques. Amsterdam, Netherlands: Elsevier.
Hasan, A. 2016. “Security of cross-country oil and gas pipelines: A risk-based model.” J. Pipeline Syst. Eng. Pract. 7 (3): 04016006. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000235.
Hosmer, D., and S. Lemeshow. 2000. Applied logistic regression. 2nd ed. New York: Wiley.
James, G., D. Witten, T. Hastie, and R. Tibshirani. 2013. An introduction to statistical learning: With applications in R. New York: Springer.
Kampelopoulos, D., G. N. Papastavrou, G. P. Kousiopoulos, N. Karagiorgos, S. K. Goudos, and S. Nikolaidis. 2020. “Machine learning model comparison for leak detection in noisy industrial pipelines.” In Proc., 2020 9th Int. Conf. on Modern Circuits and Systems Technologies (MOCAST), 1–4. Piscataway, NJ: IEEE.
Kim, J., M. Chae, J. Han, S. Park, and Y. Lee. 2021. “The development of leak detection model in subsea gas pipeline using machine learning.” J. Nat. Gas Sci. Eng. 94 (3): 104134. https://doi.org/10.1016/j.jngse.2021.104134.
Kuhn, M., and K. Johnson. 2013. Applied predictive modeling. New York: Springer.
Obida, C. B., G. A. Blackburn, J. D. Whyatt, and K. T. Semple. 2018. “Quantifying the exposure of humans and the environment to oil pollution in the Niger Delta using advanced geostatistical techniques.” Environ. Int. 111 (Jan): 32–42. https://doi.org/10.1016/j.envint.2017.11.009.
Oh, S. W., J. Bae, D. Yoon, B. Yang, G. J. Kim, and H. Soo Kim. 2018a. “A study on improvement of resource efficiency for IOT–Based pipe leak detection.” In Proc., 2018 Int. Conf. on Information and Communication Technology Convergence (ICTC), 1423–1425. Piscataway, NJ: IEEE.
Oh, S. W., D. Yoon, G. J. Kim, J. Bae, and S. H. Kim. 2018b. “Acoustic data condensation to enhance pipeline leak detection.” Nucl. Eng. Des. 327 (Feb): 198–211. https://doi.org/10.1016/j.nucengdes.2017.12.006.
Petrobras. 2020. “Saiba o que estamos fazendo para prevenir o roubo de óleo e de derivados em nossas instalações.” Accessed April 1, 2021. https://www.roubonosdutos.com.br/.
Prokhorenkova, L., G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin. 2018. “Catboost: Unbiased boosting with categorical features.” In Proc., 32nd Int. Conf. on Neural Information Processing Systems, 6639–6649. New York: Curran Associates, Inc.
Rahmati, M., H. Yazdizadeh, and A. Yazdizadeh. 2017. “Leakage detection in a gas pipeline using artificial neural networks based on wireless sensor network and internet of things.” In Proc., 2017 IEEE 15th Int. Conf. on Industrial Informatics (INDIN), 659–664. Piscataway, NJ: IEEE.
Rashid, S., U. Akram, S. Qaisar, S. A. Khan, and E. Felemban. 2014. “Wireless sensor network for distributed event detection based on machine learning.” In Proc., 2014 IEEE Int. Conf. on Internet of Things (iThings), and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom), 540–545. New York: IEEE.
Ribeiro, V. H. A., P. H. Domingues, P. R. Cavalin, G. Reynoso-Meza, H. V. Ayala, and L. F. Azevedo. 2020. “Dynamic multi-criteria classifier selection for illegal tapping detection in oil pipelines.” In Proc., 2020 Int. Joint Conf. on Neural Networks (IJCNN), 1–8. Piscataway, NJ: IEEE.
Rowen, E., A. Motil, and E. Inbar. 2020. “Novel classification of leak detection and third-party intrusion enabling best-in-class false alarm rate.” Pipeline Technol. J. 2020 (5): 36–40.
Sagi, O., and L. Rokach. 2018. “Ensemble learning: A survey.” WIREs Data Min. Knowl. Discovery 8 (4): e1249. https://doi.org/10.1002/widm.1249.
Vanhoeyveld, J., and D. Martens. 2018. “Imbalanced classification in sparse and large behaviour datasets.” Data Min. Knowl. Discovery 32 (1): 25–82. https://doi.org/10.1007/s10618-017-0517-y.
Veja. 2019. “Petrobras perde R$150 milhões por ano com furto de combustíveis.” Accessed October 16, 2021. https://veja.abril.com.br/economia/petrobras-perde-r-150-milhoes-por-ano-com-furto-de-combustiveis/.
Yale University. 2020. “The world’s most dangerous black markets.” Accessed April 1, 2021. https://yaleglobal.yale.edu/content/worlds-most-dangerous-black-markets.
Youden, W. J. 1950. “Index for rating diagnostic tests.” Cancer 3 (1): 32–35. https://doi.org/10.1002/1097-0142(1950)3:1%3C32::AID-CNCR2820030106%3E3.0.CO;2-3.
Zaoui, S. W., T. Lauber, C. Pohl, M. Kerk, T. Glaeser, and J. Wolfgang. 2020. “Machine-learning distributed-temperature-sensing-based pipeline leak detection.” In Proc., Abu Dhabi Int. Petroleum Exhibition & Conf. Calgary, AB, Canada: Society of Petroleum Engineers.
Information & Authors
Information
Published In
Journal of Pipeline Systems Engineering and Practice
Volume 14 • Issue 2 • May 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: May 9, 2022
Accepted: Dec 8, 2022
Published online: Feb 14, 2023
Published in print: May 1, 2023
Discussion open until: Jul 14, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Uma Rajasekaran, Mohanaprasad Kothandaraman, A Survey and Study of Signal and Data-Driven Approaches for Pipeline Leak Detection and Localization, Journal of Pipeline Systems Engineering and Practice, 10.1061/JPSEA2.PSENG-1611, 15, 2, (2024).
- Uma Rajasekaran, Mohanaprasad Kothandaraman, Comparative Analysis of Machine Learning and Deep Learning Based Water Pipeline Leak Detection Using EDFL Sensor, Journal of Pipeline Systems Engineering and Practice, 10.1061/JPSEA2.PSENG-1439, 14, 4, (2023).