An An Lstm-Based Anomaly Detection on Subsea Oil-Producing Well
DOI:
https://doi.org/10.29017/scog.v48i4.1819Keywords:
anomaly detection, time series classification, LSTM, offshore wells, 3W DatasetAbstract
The oil and gas industry faces substantial operational risks from anomalous events, necessitating effective Abnormal Event Management (AEM) to mitigate production losses and safety hazards. This study presents a supervised anomaly classification approach using Long Short-Term Memory (LSTM) networks on the 3W Dataset—comprising over 2,000 real, simulated, and expert-drawn events from offshore wells. Focusing on real instances with sufficient normal-state duration, the dataset was refined and segmented using observation windows of 60, 120, and 180 seconds. The models were trained on four selected pressure and temperature features and evaluated using precision, recall, and F1-score. Comparative analysis with Recurrent Neural Network (RNN) and Gated Recurrent Unit (GRU) models shows that the LSTM model consistently performs best, achieving a peak F1-score of 92% at a 120-second window. Furthermore, event-level performance analysis highlights the LSTM model’s strengths and limitations across different anomaly types. Compared to existing supervised and unsupervised methods on the 3W Dataset, the LSTM-based approach demonstrates competitive accuracy and robustness for real-time anomaly detection in offshore oil production systems.
References
Alrifaey, M., Lim, W. H., & Ang, C. K. (2021). A novel deep learning framework based RNN-SAE for fault detection of electrical gas generator. IEEE Access, 9. https://doi.org/10.1109/ACCESS.2021.3055427
Antipova, K., Klyuchnikov, N., Zaytsev, A., Gurina, E., Romanenkova, E., & Koroteev, D. (2019). Data-driven model for the drilling accidents prediction. Proceedings - SPE Annual Technical Conference and Exhibition. https://doi.org/10.2118/195888-MS
Aranha, P. E., Policarpo, N. A., & Sampaio, M. A. (2024). Unsupervised machine learning model for predicting anomalies in subsurface safety valves and application in offshore wells during oil production. Journal of Petroleum Exploration and Production Technology, 14(2). https://doi.org/10.1007/s13202-023-01720-4
Batal, I., Sacchi, L., Bellazzi, R., & Hauskrecht, M. (2009). Multivariate time series classification with temporal abstractions. In Proceedings of the 22nd International Florida Artificial Intelligence Research Society Conference (FLAIRS-22).
Blagec, K., Dorffner, G., Moradi, M., & Samwald, M. (2020, August). A critical analysis of metrics used for measuring progress in artificial intelligence.
Carvalho, B. G., Vaz Vargas, R. E., Salgado, R. M., Munaro, C. J., & Varejao, F. M. (2021). Flow instability detection in offshore oil wells with multivariate time series machine learning classifiers. In IEEE International Symposium on Industrial Electronics (ISIE 2021). https://doi.org/10.1109/ISIE45552.2021.9576310
Fernandes, W., Komati, K. S., & Assis de Souza Gazolli, K. (2024). Anomaly detection in oil-producing wells: A comparative study of one-class classifiers in a multivariate time series dataset. Journal of Petroleum Exploration and Production Technology, 14(1). https://doi.org/10.1007/s13202-023-01710-6
Figueirêdo, I. S., Vargas, R. E. V., Munaro, C. J., Varejao, F. M., & Salgado, R. M. (2021). Unsupervised machine learning applied to multivariate time series data of a rotating machine from an oil and gas platform. In IMCIC 2021 - 12th International Multi-Conference on Complexity, Informatics and Cybernetics - Proceedings.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P. A. (2019). Deep learning for time series classification: A review. Data Mining and Knowledge Discovery, 33(4), 917–963. https://doi.org/10.1007/s10618-019-00619-1
Iskandar, U. P., & Kurihara, M. (2022). Long Short-term Memory (LSTM) networks for forecasting reservoir performances in Carbon Capture, Utilisation, and Storage (CCUS) operations. Scientific Contributions Oil and Gas, 45(1), 35–51. https://doi.org/10.29017/SCOG.45.1.943
Kanyoma, I. R., Venriza, O., & Kushariyadi, K. (2023). Optimalisasi penambahan odorant pada gas menggunakan metode time series di PT. XYZ. Lembaran Publikasi Minyak dan Gas Bumi, 57(2), 43–53. https://doi.org/10.29017/LPMGB.57.2.1584
Lindemann, B., Maschler, B., Sahlab, N., & Weyrich, M. (2021). A survey on anomaly detection for technical systems using LSTM networks. Computers in Industry, 129, 103498. https://doi.org/10.1016/j.compind.2021.103498
Machado, A. P. F., Munaro, C. J., Ciarelli, P. M., & Vargas, R. E. V. (2024). Time series clustering to improve one-class classifier performance. Expert Systems with Applications, 243, 122895. https://doi.org/10.1016/j.eswa.2023.122895
Machado, A. P. F., Vargas, R. E. V., Ciarelli, P. M., & Munaro, C. J. (2022). Improving performance of one-class classifiers applied to anomaly detection in oil wells. Journal of Petroleum Science and Engineering, 218, 110983. https://doi.org/10.1016/j.petrol.2022.110983
Malhotra, P., Vig, L., Shroff, G., & Agarwal, P. (2015). Long short term memory networks for anomaly detection in time series. In 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2015) - Proceedings.
Marins, M. A., Vargas, R. E. V., Salgado, R. M., Munaro, C. J., & Varejao, F. M. (2021). Fault detection and classification in oil wells and production/service lines using random forest. Journal of Petroleum Science and Engineering, 197, 107879. https://doi.org/10.1016/j.petrol.2020.107879
Рапаков, Г. Г., Горбунов, В. А., Дианов, С. В., & Елизарова, Л. В. (2023). Research of the LSTM neural network approach in time series modeling. Cherepovets State University Bulletin, 3(114). https://doi.org/10.23859/1994-0637-2023-3-114-4
Škrlj, B., Kralj, J., Lavrač, N., & Pollak, S. (2019). Towards robust text classification with semantics-aware recurrent neural architecture. Machine Learning and Knowledge Extraction, 1(2), 646–666. https://doi.org/10.3390/make1020034
Tong, Y., Zhang, D., Guo, C., Yuan, Y., He, Y., & Li, X. (2022). Technology investigation on time series classification and prediction. PeerJ Computer Science, 8, e982. https://doi.org/10.7717/peerj-cs.982
Turan, E. M., & Jaschke, J. (2021). Classification of undesirable events in oil well operation. In Proceedings of the 2021 23rd International Conference on Process Control (PC 2021). https://doi.org/10.1109/PC52310.2021.9447527
Ulil, M. R., Winardhi, S., & Dinanto, E. (2025). Machine learning-based prediction of shear wave velocity: Performance evaluation of Bi-GRU, ANN, and the Greenberg-Castagna empirical method. Scientific Contributions Oil and Gas, 48(3). https://doi.org/10.29017/SCOG.48i3.1797
Vargas, R. E. V., de Souza, C. J. M., Varejão, F. M., de Almeida, L. R., de Oliveira, L. T., de Azevedo, J. A., & dos Santos, L. R. (2019). A realistic and public dataset with rare undesirable real events in oil wells. Journal of Petroleum Science and Engineering, 181. https://doi.org/10.1016/j.petrol.2019.106223
Published
Issue
Section
License
Copyright (c) 2025 © Copyright by Authors. Published by LEMIGAS
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors are free to Share — copy and redistribute the material in any medium or format for any purpose, even commercially Adapt — remix, transform, and build upon the material for any purpose, even commercially.
The licensor cannot revoke these freedoms as long as you follow the license terms, under the following terms Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
