Innovative Solutions for Oil Well Monitoring: Data-Driven Multiphase Virtual Flow Metering Using Ensemble Machine Learning and Historical Field Data

Wael A.  Farag; Hussein H.  Ismail; Muhammad  Nadeem

doi:10.6180/jase.202512_28(12).0010

Innovative Solutions for Oil Well Monitoring: Data-Driven Multiphase Virtual Flow Metering Using Ensemble Machine Learning and Historical Field Data

Wael A. Farag¹This email address is being protected from spambots. You need JavaScript enabled to view it., Hussein H. Ismail², and Muhammad Nadeem²

¹Electrical Power Engineering Dept., Cairo University, Giza, Egypt

²College of Engineering and Technology, American University of the Middle East, Kuwait

Received: March 5, 2025
Accepted: February 25, 2025
Publication Date: April 23, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202512_28(12).0010

By combining data-driven ensemble machine-learning algorithms and historical oil field portable test reports, this paper proposes a Data-Drive Multiphase Virtual Flow Meter (DD-MVFM) that estimates oil, gas, and water flow rates and provides real-time monitoring, and predicts future production with appropriate accuracy. The proposed DD− MVFM utilizes the existing hardware used for measurements of basic variables such as temperature, and pressure at different locations at the well-head structure. The DD − MVFM can be employed in three ways. The first way is to be used as a verification tool for multiphase physical flow meters (MPFMs), making sure they are working properly and increasing confidence in the collected readings. The second way is to use the DD−MVFM as a redundant tool when the MPFMs are not available or going through maintenance. The third way, which is the main objective of our research, is to employ the proposed DD MVFM as a stand alone for the complete replacement of current and future MPFM installments. This, significantly lowers the operating cost, reducing the required portable field tests, and saving the need to build a major infrastructure for the set-up of MPFMs for new oil wells. Consequently, this contributes to the ambitious goal of reducing CO2 emissions. The development of the DD − MVFM encompasses the fusion of multiple data wrangling and machine learning algorithms to achieve the required performance. The testing results of the proposed DD−MVFM and the prediction experiments show that it successfully achieved a performance of 85%. These results will be significantly improved in the future after incorporating more data from the previous and coming field test reports.

Keywords: Oil; Gas; Water Cut; GOR; Virtual Meter; Machine Learning; Ensemble Training

[1] A. M. Farid, A. H. El-Banbi, and A. A. Abdelwaly, (2013) “An integrated model for history matching and predicting reservoir performance of gas/condensate wells" SPE Reservoir Evaluation & Engineering 16(04): 412–422. DOI: 10.2118/151869-pa.
[2] H. Ghorbani, D. A. Wood, A. Choubineh, N. Mo hamadian, A. Tatar, H. Farhangian, and A. Nikooey, (2020) “Performance comparison of bubble point pressure from oil PVT data: Several neurocomputing techniques compared" Experimental and Computational Multiphase Flow 2: 225–246. DOI: 10.1007/s42757-019-0047-5.
[3] A.F. Ibrahim, A. Assem, and M. Ibrahim, (2020) “A novel workflow for water flowback RTA analysis to rank the shale quality and estimate fracture geometry" Journal of Natural Gas Science and Engineering 81: 103387. DOI: 10.1016/j.jngse.2020.103387.
[4] T. Bikmukhametov and J. Jäschke. “Oil production monitoring using gradient boosting machine learn ing algorithm”. In: IFAC-PapersOnLine. 52. Elsevier B.V., 2019, 514–519. DOI: 10.1016/j.ifacol.2019.06.114.
[5] R. A. Dhaif, A. F. Ibrahim, S. Elkatatny, and D. A. Shehri, (2021) “Prediction of oil rates using Machine Learning for high gas oil ratio and water cut reservoirs" Flow Measurement and Instrumentation 82: 102065. DOI: 10.1016/j.flowmeasinst.2021.102065.
[6] A.Alsalman, A. Almutairi, S. Alsyed, and V. Kumar. “First time utilization of portable multiphase flow meter for testing offshore wells in Saudi Arabia”. In: SPE Middle East Oil and Gas Show and Conference. SPE. 2015, SPE–172696.
[7] G. Falcone, G. F. Hewitt, C. Alimonti, and B. Harrison. “Multiphase Flow Metering: Current Trends and Future Developments”. In: Proceedings- SPE An nual Technical Conference and Exhibition. Society of Petroleum Engineers (SPE), 2001, 1291–1303. DOI: 10.2118/71474-ms.
[8] W. AS. Fluid Classification. https://wiki.whitson. com/phase_behavior/classification/reservoir_ f luid_type/ [Accessed: 9th March 2023]. 2022.
[9] A. Mirzaei-Paiaman and S. Salavati, (2013) “A new empirical correlation for sonic simultaneous flow of oil and gas through wellhead chokes for persian oil fields" Energy Sources, Part A: Recovery, Utilization and Environmental Effects 35: 817–825. DOI: 10.1080/15567031003773304.
[10] N.Woodroof. Why traditional methods of validating multiphase flow meters are not delivering– part two. https: //www.oilfieldtechnology.com/special-reports/ 23012020/why-traditional-methods-of-validating multiphase-flow-meters-are-not-delivering-part two/ [Accessed: 9th March 2023]. 2020.
[11] M. F. METERING. Handbook of Multiphase Flow Metering. Norwegian Society for Oil and Gas Measurement, 2005.
[12] M.A.Kargarpour, (2019) “Oil and gas well rate estimation by choke formula: semi-analytical approach" Journal of Petroleum Exploration and Production Technology 9: 2375–2386. DOI: 10.1007/s13202-019-0629-6.
[13] W. E. Gilbert, (1954) “Flowing and Gas-Lift Well Performance" API Drilling and Production Practice 13: 126–157.
[14] B. Guo, W. C. Lyons, and A. Ghalambor, (2007) “5 Choke performance" Petroleum production engineer ing: 59–67. DOI: 10.1016/B978-075068270-1/50009-8.
[15] A. Sircar, K. Yadav, K. Rayavarapu, N. Bist, and H. Oza, (2021) “Application of machine learning and artificial intelligence in oil and gas industry" Petroleum Research 6: 379–391. DOI: 10.1016/j.ptlrs.2021.05.009.
[16] H. K. Mohammad, M. H. AlEad, A. A. Abdullah, A. A.Hussain, A.A.G.Mohammad, and W.A.Farag. “AnIoT-based condition-boosting solution for the oil upstream industry”. In: 2022 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT). IEEE. 2022, 380–386. DOI: 10.1109/3ICT56508.2022.9990887.
[17] M.Mohammadpoor and F.Torabi, (2020) “Big Data analytics in oil and gas industry: An emerging trend" Petroleum 6: 321–328. DOI: 10.1016/j.petlm.2018.11.001.
[18] Ensemble learning. https://en.wikipedia.org/wiki/Ensemble_learning [Accessed: 9th March 2023].
[19] Equation of state. https://www.thermopedia.com/content/734/ [Accessed: 9th March 2023].
[20] H. Klie. A Tale of Two Approaches: Physics-Based vs. Data-Driven Models. https://jpt.spe.org/a-tale-of two-approaches-physics-based-vs-data-driven models [Accessed: 10th March 2023]. 2021.
[21] S. Song, M. Wu, J. Qi, H. Wu, Q. Kang, B. Shi, S. Shen, Q. Li, H. Yao, H. Chen, and J. Gong, (2022) “An intelligent data-driven model for virtual flow meters in oil and gas development" Chemical Engineering Research and Design 186: 398–406. DOI: 10.1016/j.cherd.2022.08.016.
[22] Decision tree learning. https://en.wikipedia.org/ wiki/Decision_tree_learning [Accessed: 10th March 2023].
[23] D. Ravindran. Tree-Based Machine Learning Algorithms Explained. https://medium.com/analytics vidhya/tree-based-machine-learning-algorithms explained- b50937d3cf8e [Accessed: 10th March 2023].
[24] Black box. https://en.wikipedia.org/wiki/Black_box [Accessed: 10th March 2023].
[25] F. A. Anifowose, J. Labadin, and A. Abdulraheem, (2017) “Ensemble machine learning: An untapped modeling paradigm for petroleum reservoir characterization" Journal of Petroleum Science and Engineering 151: 480–487. DOI: 10.1016/j.petrol.2017.01.024.
[26] M.D.AlAjmi, S. A. Alarifi, and A. H. Mahsoon. “Im proving multiphase choke performance prediction and well production test validation using artificial intelligence: a new milestone”. In: SPE digital energy conference and exhibition. SPE. 2015, D031S022R003.
[27] S. Kalam, M. R. Khan, Z. Tariq, F. A. Siddique, A. Ab dulraheem, and R. A. Khan. “A novel correlation to predict gas flow rates utilizing artificial intelligence: Anindustrial 4.0 approach”. In: Society of Petroleum Engineers- SPE/PAPG Pakistan Section Annual Technical Symposium and Exhibition 2019, PATS 2019. Society of Petroleum Engineers, 2019. DOI: 10.2118/201170-MS.
[28] W. Farag, V. Quintana, and G. Lambert-Torres. “Neuro-Fuzzy Modeling of Complex Systems Using Genetic Algorithms”. In: IEEE International Confer ence on Neural Networks (IEEE ICNN’97). IEEE, 1997. DOI: 10.1109/ICNN.1997.611709.
[29] B. Bahrami, S. Mohsenpour, H. R. S. Noghabi, N. Hemmati, and A. Tabzar, (2019) “Estimation of flow rates of individual phases in an oil-gas-water multiphase f low system using neural network approach and pressure signal analysis" Flow Measurement and Instrumentation 66: 28–36. DOI: 10.1016/j.flowmeasinst.2019.01.018.
[30] Difference Between Skewness and Kurtosis. https://www.analyticsvidhya.com/blog/2021/05/shape of-data-skewness-and-kurtosis/ [Accessed: 10th March 2023].
[31] OLGADynamic Multiphase Flow Simulator. https://www.software.slb.com/products/olga [Accessed: 10th March 2023].
[32] K. O. Company. Kuwait Oil Company. https://www.kockw.com/sites/EN/Pages/Default.aspx [Accessed: 10th March 2023].
[33] S. (SLB). Schlumberger Kuwait. https://www.slb.com/about/who-we-are/our-global-footprint/slbkuwait [Accessed: 10th March 2023].
[34] Bottom Hole Pressure Survey. https://oilfieldbeginner. com/bottom-hole-pressure-survey/ [Accessed: 11th March 2023].
[35] Perforation (oil well). https://en.wikipedia.org/wiki/ Perforation_(oil_well) [Accessed: 11th March 2023].
[36] Well completion reports (WCR). https://researchdata.edu.au/completion-reports-wcr/181026 [Accessed: 11th March 2023].
[37] Well completion– oil gas wells. https://www. deepdata.com/well-completion/[Accessed: 11th March 2023].
[38] S. (SLB). Electric Submersible Pumps. https://www.slb.com/completions/artificial- lift/electrical submersible-pumps [Accessed: 11th March 2023].
[39] S. (SLB). Mobile Production Testing. {https://www.slb.com/reservoir-characterization/reservoir testing/surface-testing/mobile-production-testing} [Accessed:11thMarch2023].
[40] Pearson correlation coefficient. https://en.wikipedia.org/wiki/Pearson_correlation_coefficient [Accessed: 11th March 2023].
[41] scikit-learn developers. Sklearn Standard Scaler. https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler. html [Ac cessed: 12th March 2023].
[42] scikit-learn developers. Sklearn Min-Max-Scaler. https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.MinMaxScaler. html [Accessed: 12th March 2023].
[43] M. Nielsen. Chapter 2: How the backpropagation algo rithm works. http://neuralnetworksanddeeplearning. com/chap2.html [Accessed: 12th March 2023]. 2019.
[44] G. Ke, Q. Meng, T. Finley, W. Chen, W. Ma, Q. Ye, and T.-Y. L. Liu, (2017) “LightGBM: A Highly Efficient Gradient Boosting Decision Tree" Advances in neural information processing systems 30:
[45] Feedforward neural network. https://en.wikipedia.org/wiki/Feedforward_neural_network [Accessed: 12th March 2023].
[46] LightGBM. https://en.wikipedia.org/wiki/LightGBM[Accessed: 12th March 2023].
[47] XGBoost. https://en.wikipedia.org/wiki/XGBoost [Accessed: 12th March 2023].
[48] Random forest. https://en.wikipedia.org/wiki/ Random_forest [Accessed: 12th March 2023].
[49] API gravity. https://en.wikipedia.org/wiki/API_ gravity [Accessed: 12th March 2023].
[50] W.Farag, V. Quintana, and G. Lambert-Torres. “Ge netic algorithms and back-propagation: a comparative study”. In: IEEE Canadian Conference on Electrical and Computer Engineering. IEEE, 1998. DOI: 10.1109/CCECE.1998.682559.
[51] Gradient boosting. https://en.wikipedia.org/wiki/ Gradient_boosting [Accessed: 13th March 2023].
[52] W.A.Farag, V. H. Quintana, and G. Lambert-Torres, (1998) “A genetic-based neuro-fuzzy approach for modeling and control of dynamical systems" IEEE Transactions on neural Networks 9(5): 756–767.
[53] machine learning plus. An Introduction to Gradient Boosting Decision Trees. https://www.machinelearningplus.com/machine-learning/an introduction-to-gradient-boosting-decision-trees/ [Accessed: 13th March 2023].