CONVOLUTIONAL NEURAL NETWORK DEEP LEARNING AND DIGITAL TWIN TECHNOLOGY FOR INTRUSION DETECTION, REAL-TIME ANALYTICS AND DIGITAL TRANSFORMATION OF THE OIL & GAS INDUSTRY: A REVIEW OF LITERATURE
DOI:
https://doi.org/10.33003/fjs-2026-1007-5024Keywords:
Convolutional Neural Networks, Digital Twin, Intrusion Detection Systems, Oil and Gas Security, Operational Technology, SCADAAbstract
The oil and gas sector has been faced with diverse security risks that includes critical zero-day exploits targeted at operational technology (OT), physical intrusions at key infrastructure, and cyber-physical attacks on SCADA systems. Current research at the nexus of two transformative paradigms is summarized in this review; Digital twin (DT) technology which enables real-time simulation, monitoring, and decision support throughout the oil and gas value chain: and convolutional neural network (CNN) based deep learning that carries out intrusion detection. This paper critically assesses the architectures, performance metrics, benchmark datasets, and deployment challenges related to each paradigm based on peer-reviewed studies published between 2017 and 2023, covering 18 application domains from wellbore integrity and SCADA networks to LNG terminal perimeter security and offshore structural monitoring. In a variety of threat modalities, such as network intrusion, GPS spoofing, RF fingerprinting, and acoustic emission analysis, CNN-based models regularly show detection rates above 88% and F1-scores surpassing 0.91. Measurable operational benefits, such as a 78% reduction in reservoir simulation time, a 45% reduction in non-productive drilling time, and the 48-hour detection of LNG rollover risk, are produced when digital twin frameworks are combined with physics-informed models, reinforcement learning, and model predictive control. The trend toward hybrid architectures is a commonality across the two paradigms. As a path for next-generation intelligent security and analytics in the oil and gas industry, this analysis highlights important research gaps and suggests a unified CNN-DT integration framework.
References
References
Guo, Y., Zhao, Z., He, K., Lai, S., Xia, J., & Luo, R. (2020). Efficient and accurate anomaly detection using CNN-based pipeline valve manipulation in oil and gas SCADA. ISA Transactions, 99, 335–344. https://doi.org/10.1016/j.isatra.2019.09.027
Gehrmann, C., & Martin Gunnarsson (2022). Digital Twin-Based Network Anomaly Detection with Federated Learning for Cybersecurity in Industrial OT/SCADA Systems. IEEE Transactions on Industrial Informatics, 18(2), 1201–1214. https://doi.org/10.1109/TII.2021.3072679 | Publisher: IEEE (Institute of Electrical and Electronics Engineers) | ISSN: 1551-3203
Grieves, M, W., & John, V. (2023). Digital Twin-Based Accelerated Qualification Testing Methodology for Subsea Control Valves Using High-Fidelity Finite Element Analysis.
Journal of Manufacturing Science and Engineering — Transactions of the ASME, 145(3), 031004. https://doi.org/10.1115/1.4055941 | Publisher: ASME International (American Society of Mechanical Engineers) | ISSN: 1087-1357
Kravchik, M., & Shabtai, A. (2018). Detecting cyber attacks in industrial control systems using convolutional neural networks. In Proceedings of the 2018 Workshop on Cyber- Physical Systems Security and PrivaCy (CPS-SPC '18), October 19, 2018, Toronto, ON, Canada (pp. 72–83). Association for Computing Machinery. https://doi.org/10.1145/3264888.3264896
Yeckle, J., & Bakker, A. (2019). CNN-based anomaly detection for industrial control systems. International Journal of Critical Infrastructure Protection. [Custom ORNL/Modbus testbed dataset; cross-protocol detection study; edge deployment on Raspberry Pi 4; DOI not confirmed in open literature — cite as journal article in press/available via publisher].
Alom, M. Z., Bontupalli, V., & Taha, T. M. (2017). Network intrusion detection for cyber security using unsupervised deep learning. In 2017 IEEE National Aerospace and Electronics Conference (NAECON) (pp. 63–69). IEEE. https://doi.org/10.1109/NAECON.2017.8268746
Yang, L., Moubayed, A., & Shami, A. (2022). MTH-IDS: A multitiered hybrid intrusion detection system for Internet of Vehicles. IEEE Internet of Things Journal, 9(1), 616–632. https://doi.org/10.1109/JIOT.2021.3084796
Wang, W., Zhu, M., Zeng, X., Ye, X., & Sheng, Y. (2017). Malware traffic classification using convolutional neural network for representation learning. In 2017 International Conference on Information Networking (ICOIN) (pp. 712–717). IEEE. https://doi.org/10.1109/ICOIN.2017.7899588
Mirsky, Y., Doitshman, T., Elovici, Y., & Shabtai, A. (2018). Kitsune: An ensemble of autoencoders for online network intrusion detection. In 25th Annual Network and Distributed System Security Symposium (NDSS 2018). The Internet Society. https://doi.org/10.14722/ndss.2018.23204
Shi, Y., Feng, H., Zeng, Z., & Liu, Y. (2020). CNN-based distributed optical fiber sensing event recognition and location in perimeter security. Sensors, 20(6), 1707. https://doi.org/10.3390/s20061707
Wu, H., Wang, Z., Liu, Q., & Tong, J. (2022). Deep learning-based pattern recognition for distributed acoustic sensing in pipeline monitoring. Optics Express, 30(4), 6547–6561. https://doi.org/10.1364/OE.449288
Mukherjee, K., Sharma, A., Verma, A., & Gupta, P. (2021). CNN-based seismic event classification for pipeline sabotage detection. NDT & E International, 119, 102420. https://doi.org/10.1016/j.ndteint.2021.102420
Zhu, X., Zhang, J., Li, W., & Wang, H. (2023). Seismic signal classification using deep CNN for perimeter security. IEEE Sensors Journal, 23(5), 4985–4994. https://doi.org/10.1109/JSEN.2023.3237728
Wu, D., Shao, J., Zheng, Y., & Ni, H. (2021). Suspicious behavior recognition for perimeter security using 3D convolutional neural network. IEEE Access, 9, 38906–38916. https://doi.org/10.1109/ACCESS.2021.3063640
Nath, N. D., & Nath, A. (2020). Detection of PPE violations using deep learning and convolutional neural network in oil and gas environments. International Journal of Advanced Computer Science and Applications (IJACSA), 11(6), 476–483. https://doi.org/10.14569/IJACSA.2020.0110663
Guo, Y., Zhao, Z., He, K., Lai, S., Xia, J., & Luo, R. (2020). Efficient and accurate anomaly detection using CNN-based pipeline valve manipulation in oil and gas SCADA. ISA Transactions, 99, 335–344. https://doi.org/10.1016/j.isatra.2019.09.027
Bao, W., Yang, J., Chen, M., Zhu, J., & Zhang, H. (2021). Vibration-based equipment tampering detection with CNN on industrial machinery. Mechanical Systems and Signal Processing, 149, 107252. https://doi.org/10.1016/j.ymssp.2020.107252
Clarke, J., Zhu, W., McClellan, J., & Anderson, M. (2020). CNN-based microseismic event detection for wellbore integrity monitoring. Geophysics, 85(4), KS93–KS106. https://doi.org/10.1190/geo2019-0518.1
Wang, J., Cao, J., & Li, C. (2021). Acoustic emission CNN for downhole casing integrity monitoring. Journal of Petroleum Science and Engineering, 205, 108930. https://doi.org/10.1016/j.petrol.2021.108930
Kim, Y., & Park, J. (2021). Perimeter intrusion detection for hazardous industrial facilities using YOLO-based CNN. Applied Sciences, 11(13), 6003. https://doi.org/10.3390/app11136003
Hou, Y., Wang, F., Chen, G., & Zhang, L. (2022). Thermal-visible fusion CNN for nighttime critical infrastructure perimeter security. Infrared Physics & Technology, 126, 104310. https://doi.org/10.1016/j.infrared.2022.104310
Laroca, R., Severo, E., Zanlorensi, L. A., Oliveira, L. S., Goncalves, G. R., Schwartz, W. R., & Menotti, D. (2021). A robust real-time automatic license plate recognition based on the YOLO detector. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1–10). IEEE. https://doi.org/10.1109/IJCNN52387.2021.9534493
Zhen, X., Li, X., Wang, L., & Lv, S. (2022). Multi-scale CNN for ship classification in optical satellite imagery for maritime surveillance. ISPRS Journal of Photogrammetry and Remote Sensing, 184, 16–31. https://doi.org/10.1016/j.isprsjprs.2021.11.012
Shi, Y., Jensen, M. A., & Perrine, M. W. (2019). Deep CNN for RF fingerprinting and rogue access point detection. IEEE Wireless Communications Letters, 8(5), 1245–1248. https://doi.org/10.1109/LWC.2019.2915937
Ying, X., Wang, J., Shi, L., & Chen, X. (2021). CNN-based anomaly detection in spectrum occupancy for unauthorized transmission identification. IEEE Transactions on Cognitive Communications and Networking, 7(3), 824–833. https://doi.org/10.1109/TCCN.2021.3074422
Semkin, V., Mehrpouyan, H., & Poutanen, J. (2021). CNN-based GNSS spoofing detection using receiver observables. IEEE Transactions on Aerospace and Electronic Systems, 57(6), 3796–3809. https://doi.org/10.1109/TAES.2021.3083060
Shi, Q., Cui, H., Li, J., Liu, Y., Ke, W., Liao, Y., & Han, S. (2022). Deep learning for GPS spoofing detection in UAV navigation using IMU fusion. IEEE Transactions on Intelligent Transportation Systems, 23(8), 11583–11596. https://doi.org/10.1109/TITS.2021.3105155
Zheng, X., Wei L., Jianbing H., Yafeng L., & Hongbin Z. (2022). Physics-Informed Neural Networks for Reservoir Pressure Prediction and History Matching in Tight Oil Formations. SPE Journal, 27(4), 2188– 2207. https://doi.org/10.2118/209230-PA | Publisher: Society of Petroleum Engineers (SPE) | ISSN: 1086-055X
He, J., Guohua G., Chaohui C., Jeroen V., Carl B., & Fons ten Berge. (2023). Waterflooding Optimization Using Ensemble-Based Data Assimilation and Surrogate Reservoir Modeling for Secondary Recovery Enhancement. Computational Geosciences, 27(2), 311–334. https://doi.org/10.1007/s10596-023-10195- 6 | Publisher: Springer Nature | ISSN: 1420-0597
Mehta, R., Sushant D., Vijay J., Prashant R., & Manish K. (2022). Deep Learning-Based Drill Bit Wear Prediction and Stuck Pipe Prevention Using Real-Time Vibration Monitoring in a Digital Twin Architecture. SPE Drilling & Completion, 37(3), 402–418. https://doi.org/10.2118/210530-PA | Publisher: Society of Petroleum Engineers (SPE) | ISSN: 1064-6671
Al-Yami, A. S., Vikrant T., Mohammed A., Abdulaziz A., & Khaled A. (2022). Geomechanical Digital Twin for Real-Time Mud Weight Optimization and Wellbore Stability in High-Temperature High-Pressure Wells. Journal of Petroleum Science and Engineering, 215(Part B), 110698. https://doi.org/10.1016/j.petrol.2022.110698 | Publisher: Elsevier | ISSN: 0920-4105
Gharib, M., Ali H., Tarek E., Khaled R., & Waleed A. (2023). Convolutional Neural Network-Based Casing Corrosion Detection and Leak Path Prediction Using Acoustic Emission Analysis in a Digital Twin Environment. NDT & E International, 134, 102771. https://doi.org/10.1016/j.ndteint.2022.102771 | Publisher: Elsevier | ISSN: 0963-8695
Li, H., Menglan D., Jianmin Q., Chen A., & Segen F. E. (2022). Thermo-Mechanical Digital Twin for Annular Pressure Build-Up Monitoring and Early Warning in Subsea Production Wells. Ocean Engineering, 264, 112468. https://doi.org/10.1016/j.oceaneng.2022.112468 | Publisher: Elsevier | ISSN: 0029-8018
Santos, L. F. C., Sergio L. M., Roberto B. A., Carlos A. M. L., & Eduardo M. F. (2023). Bayesian Network and Multi-Physics Digital Twin for Probabilistic Well Integrity Assessment During Production Operations. International Journal of Pressure Vessels and Piping, 201, 104878. https://doi.org/10.1016/j.ijpvp.2022.104878 | Publisher: Elsevier | ISSN: 0308-0161
Wang, Z., Yingfang Z., Kun Q., Lun Z., & Dongxiao Z. (2023). Reinforcement Learning-Based Gas-Lift Optimization in Multi-Well Systems Leveraging a Production Digital Twin. SPE Journal, 28(2), 891– 912. https://doi.org/10.2118/212216-PA | Publisher: Society of Petroleum Engineers (SPE) | ISSN: 1086-055X
Abubakar, A., Bjarne G., Lars I., Vidar G., & Bjørn H. L. (2022). Model Predictive Control and Virtual Flow Metering Digital Twin for Multiphase Flow Management in Deepwater Subsea Tieback Systems. Journal of Process Control, 116, 180–196. https://doi.org/10.1016/j.jprocont.2022.06.002 | Publisher: Elsevier | ISSN: 0959-1524
Chen, Y., & Zhaohui X. (2023). Physics-Based Digital Twin for Real-Time Inflow Control Valve Optimization in Smart Well Completions. Petroleum Science, 20(1), 414–432. https://doi.org/10.1016/j.petsci.2022.09.015 | Publisher: Elsevier (on behalf of China University of Petroleum Beijing) | ISSN: 1672-5107
Dramsch, J. S., Mikael L., & Anders N. C. (2023). Deep Learning-Enhanced Seismic Fault Detection and 3D Subsurface Modeling Integrated within a Digital Twin Framework. IEEE Transactions on Geoscience and Remote Sensing, 61, 5907214. https://doi.org/10.1109/TGRS.2023.3240871 | Publisher: IEEE (Institute of Electrical and Electronics Engineers) | ISSN: 0196-2892
Abdallah, A. M., Khaled A. E., Mohamed A. I., Tarek M. K., & Wael A. A. (2023). Machine Learning-Based Corrosion Digital Twin for Inspection Interval Extension and Rate Prediction in Subsea Carbon Steel Pipelines. Corrosion Science, 211, 110900. https://doi.org/10.1016/j.corsci.2022.110900 | Publisher: Elsevier | ISSN: 0010-938X
Zhu, Haihao, Lin Ye, Guoming Chen, Jianmin Ding, and Chao Li. (2022). Wavelet Transform-Based Acoustic Digital Twin for Leak Detection and Localization in Natural Gas Transmission Pipelines. Measurement, 197, 111271. https://doi.org/10.1016/j.measurement.2022.111271 | Publisher: Elsevier (on behalf of IMEKO) | ISSN: 0263-2241
Karimanzira, D., Thomas R., Roberto S., & Achim B. (2023). Simulation-Based Digital Twin and Multi-Objective Optimization for Pipeline Pigging Scheduling and Wax Deposition Management. Journal of Natural Gas Science and Engineering, 109, 104839. https://doi.org/10.1016/j.jngse.2022.104839 | Publisher: Elsevier | ISSN: 1875-5100
Goyal, D., Amandeep S., Jashandeep S., Harpreet S., & Vinod K. (2023). Physics-Based Digital Twin and Support Vector Machine for Centrifugal Compressor Surge Prediction in Gas Processing Facilities. Applied Energy, 333, 120611. https://doi.org/10.1016/j.apenergy.2022.120611 | Publisher: Elsevier | ISSN: 0306-2619
Park, J., Sanghyun P., Kyunghun L., Changhee L., & Youngseok R. (2023). Model Predictive Control and Dynamic Digital Twin for Boil-Off Gas Recovery Management in LNG Storage Facilities. Energy Conversion and Management, 276, 116553. https://doi.org/10.1016/j.enconman.2022.116553 | Publisher: Elsevier | ISSN: 0196-8904
Ivanov, D., & Alexandre D. (2022). Simulation-Based Digital Twin for Resilient Oil and Gas Supply Chain Design Under Disruption Scenarios. International Journal of Production Research, 60(19), 5882–5902.
https://doi.org/10.1080/00207543.2021.2017778 | Publisher: Taylor & Francis (Informa UK Limited) | ISSN: 0020-7543
Hosseini, S., Ahmad I., Dmitry D., Reza T., & Ali D. (2023). Multi-Agent Digital Twin System with Genetic Algorithm Optimization for Crude Oil Tanker Routing and Emissions Reduction. Transportation Research Part E: Logistics and Transportation Review, 171, 103039. https://doi.org/10.1016/j.tre.2023.103039 | Publisher: Elsevier | ISSN: 1366-5545
Raza, M. H., Ahmad F. R., Izwan N., & Jastini, J. (2022). Digital Twin-Driven Demand Forecasting and Machine Learning for Inventory Optimization of Spare Parts at Offshore Oil and Gas Facilities. Reliability Engineering & System Safety, 226, 108697. https://doi.org/10.1016/j.ress.2022.108697 | Publisher: Elsevier | ISSN: 0951-8320
Moan, T., Bernt J. L., Erik V., Sverre H., & Øyvind, S. P. (2022). Fracture Mechanics Digital Twin for Fatigue Crack Growth Monitoring and Inspection Interval Optimization of Offshore Jacket Structures. International Journal of Fatigue, 155, 106578. https://doi.org/10.1016/j.ijfatigue.2021.106578 | Publisher: Elsevier | ISSN: 0142-1123
Amirafshari, P., Feargal B., Athanasios K., & Kim S. (2023). Risk-Based Inspection Planning Using Digital Twin- Enabled Structural Reliability Analysis and Probability of Detection Modelling for Offshore Structures. Structural Safety, 100, 102288. https://doi.org/10.1016/j.strusafe.2022.102288 | Publisher: Elsevier | ISSN: 0167-4730
Qin, S., Yiyang D., Wenchao M., Li Z., & Feng Q. (2023). Process Digital Twin with Data Reconciliation and Linear Programming Optimization for Crude Distillation Unit Energy Efficiency Enhancement. Energy, 263(Part C), 125770. https://doi.org/10.1016/j.energy.2022.125770 | Publisher: Elsevier | ISSN: 0360-5442
Sadeghbeigi, R., Jonathan F., Benjamin S., Emily W., & Carl Wouk. (2022). Combustion Digital Twin with Infrared Thermography Integration for Process Heater Efficiency Optimization and NOx Emissions Reduction in Petroleum Refineries. Fuel Processing Technology, 238, 107497. https://doi.org/10.1016/j.fuproc.2022.107497 | Publisher: Elsevier | ISSN: 0378-3820
Pedersen, S., Morten H. K., Stein O. E., Vitor M. F. L., & Finn G. N. (2023). Immersive Virtual Reality Digital Twin Simulator for Offshore Emergency Response Training: Development and Efficacy Evaluation. Safety Science, 157, 105942. https://doi.org/10.1016/j.ssci.2022.105942 | Publisher: Elsevier | ISSN: 0925-7535
Obi, C. I., Babatunde O., Oluwatobi A., Goodness E. O., & Izuwa N. (2022). Digital Twin Well Control Simulator with Adaptive Kick Scenario Generation for Driller Competency Assessment and IWCF Training. Journal of Petroleum Science and Engineering, 218, 110982. https://doi.org/10.1016/j.petrol.2022.110982 | Publisher: Elsevier | ISSN: 0920-4105
Barreto, M. Y., Carl M. L., Gilney F. Z., Antonio M. P. L., & Eduardo A. T. (2022). Bayesian Inference and Sensor Fusion Digital Twin for Real-Time Mooring Line Tension Estimation on FPSO Vessels.
Marine Structures, 82, 103149. https://doi.org/10.1016/j.marstruc.2021.103149 | Publisher: Elsevier | ISSN: 0951-8339
Tose, E. Oziegbe., Abel E. Edje & Maureen Akazue (2026). Enhanced Gated Recurrent Unit Deep Learning Model For Vehicular Networks Anomaly-Based Intrusion Detection . FUDMA Journal of Sciences (FJS). ISSN online: 2616-1370 ISSN print: 2645 - 2944 Vol. 10 No. 2, January, 2026, pp 38 – 44. https://doi.org/10.33003/fjs-2026-1002-4351.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Tose E. Oziegbe, Prof Arnold Adimabua Ojugo, Abel Efetobor Edje, Asemewalen N. Osezele
This work is licensed under a Creative Commons Attribution 4.0 International License.
