Optimized neural networks for efficient modeling of crude oil production
DOI:
https://doi.org/10.1007/s10115-025-02415-4Keywords:
Crude oil production , machine learning in geoscience , Multilayer perceptron neural networkAbstract
The accurate prediction of crude oil production is crucial for effective management of oil reservoir operations. This paper leverages recent advancements in machine learning techniques and metaheuristic optimization algorithms, specifically deep learning (DL) and metaheuristic (MH) approaches, to construct a robust and efficient oil production prediction model. Real-world datasets from two diverse countries, Yemen and China, are employed in model development. The study focuses on optimizing a multilayer perceptron (MLP) using the Runge–Kutta optimizer (RUN). The primary goal is to enhance the MLP parameters through the application of the RUN algorithm. Rigorous evaluation experiments gauge the efficacy of the resulting prediction model (RUN-MLP), demonstrating impressive performance across three widely recognized evaluation metrics: root-mean-square error (RMSE), mean absolute error (MAE), and coefficient of determination (). Comparative analyses involve multiple MLP-modified models employing various MH algorithms, with the RUN-MLP consistently exhibiting competitive performance. The findings underscore the computational efficiency of the RUN optimization algorithm. Additionally, the study employs the Friedman test as a statistical tool to elucidate differences between RUN and its competitors.
References
A
Ahmadianfar, I., Heidari, A. A., Gandomi, A. H., Chu, X., & Chen, H. (2021). Run beyond the metaphor: An efficient optimization algorithm based on Runge Kutta method. Expert Systems with Applications, 181, Article 115079. https://doi.org/10.1016/j.eswa.2021.115079
Al-Areeq, N. M., & Maky, A. F. (2015). Organic geochemical characteristics of crude oils and oil-source rock correlation in the Sunah oilfield, Masila region, eastern Yemen. Marine and Petroleum Geology, 63, 17–27. https://doi.org/10.1016/j.marpetgeo.2015.02.008
Al-Mudhafar, W. J. (2020). Integrating machine learning and data analytics for geostatistical characterization of clastic reservoirs. Journal of Petroleum Science and Engineering, 195, Article 107837. https://doi.org/10.1016/j.petrol.2020.107837
Al-Mudhafar, W. J., & Wood, D. A. (2024). Development and simulation of the gas-downhole water sink-assisted gravity drainage (gdws-agd) process to reduce carbon footprint and improve clean oil production by injecting CO2 and petroleum-associated gas. Journal of Cleaner Production, 456, Article 142792. https://doi.org/10.1016/j.jclepro.2024.142792
Al-Shabandar, R., Jaddoa, A., Liatsis, P., & Hussain, A. J. (2021). A deep gated recurrent neural network for petroleum production forecasting. Machine Learning with Applications, 3, Article 100013. https://doi.org/10.1016/j.mlwa.2020.100013
Aoun, E. E., Pu, H., Rasouli, V., Tomomewo, O., Khetib, Y., & Ameur, M. (2024). Enhanced oil recovery through alternating gas re-injection to reduce gas flaring in the Bakken. Energy, 290, Article 130103. https://doi.org/10.1016/j.energy.2023.130103
Asante, J., Ampomah, W., Tu, J., & Cather, M. (2024). Data-driven modeling for forecasting oil recovery: A timeseries neural network approach for tertiary CO2 wag EOR. Geoenergy Science and Engineering, 233, Article 212555. https://doi.org/10.1016/j.geoen.2023.212555
B
Basheer, I. A., & Hajmeer, M. (2000). Artificial neural networks: Fundamentals, computing, design, and application. Journal of Microbiological Methods, 43Trace(1), 3–31. https://doi.org/10.1016/S0167-7012(00)00201-3
Boret, S., & Marin, O. R. (2019). Development of surrogate models for CSI probabilistic production forecast of a heavy oil field. Mathematics and Computers in Simulation, 164, 63–77. https://doi.org/10.1016/j.matcom.2019.01.002
C
Chang, J., Zhang, D., Li, Y., Lv, W., & Xiao, Y. (2023). Physics-constrained sequence learning with attention mechanism for multi-horizon production forecasting. Geoenergy Science and Engineering, 231, Article 212388. https://doi.org/10.1016/j.geoen.2023.212388
Chen, G., Tian, H., Xiao, T., Xu, T., & Lei, H. (2024). Time series forecasting of oil production in enhanced oil recovery system based on a novel CNN-GRU neural network. Geoenergy Science and Engineering, 233Trace, Article 212528. https://doi.org/10.1016/j.geoen.2023.212528
Cheng, Y., & Yang, Y. (2021). Prediction of oil well production based on the time series model of optimized recursive neural network. Petroleum Science and Technology, 39(9-10), 303–312. https://doi.org/10.1080/10916466.2021.1901721
D
Davtyan, A., Rodin, A., Muchnik, I., & Romashkin, A. (2020). Oil production forecast models based on sliding window regression. Journal of Petroleum Science and Engineering, 195, Article 107916. https://doi.org/10.1016/j.petrol.2020.107916
de Oliveira, W. R., Prates, R., Moura, R., Gonçalves, M. M., Castro, M., Soriano-Vargas, A., Júnior, P., Hossain, M. M., Zampieri, M. F., & Ferreira, A. (2022). Data-driven deep-learning forecasting for oil production and pressure. Journal of Petroleum Science and Engineering, 210, Article 109937. https://doi.org/10.1016/j.petrol.2021.109937
E
Eberhart, R., & Kennedy, J. (1995). A new optimizer using particle swarm theory. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, 39–43. https://doi.org/10.1109/MHS.1995.494215
Elmabrouk, S., Shirif, E., & Mayorga, R. (2014). Artificial neural network modeling for the prediction of oil production. Petroleum Science and Technology, 32(9), 1123–1130. https://doi.org/10.1080/10916466.2011.644141
H
Hakimi, M. H., Abdullah, W. H., & Al Areeq, N. M. (2014). Organic geochemical characteristics and depositional environments of the upper cretaceous coals in the Jiza-qamar basin of eastern Yemen. Fuel, 118, 335–347. https://doi.org/10.1016/j.fuel.2013.11.002
Hakimi, M. H., Al Qadasi, B. A., Al Sharrabi, Y., Al Sorore, O. T., & Al Samet, N. G. (2017). Petrophysical properties of cretaceous clastic rocks (qishn formation) in the Sharyoof oilfield, onshore Masila basin, Yemen. Egyptian Journal of Petroleum, 26(2), 439–455. https://doi.org/10.1016/j.ejpe.2016.06.004
Holland, J. H. (1992). Genetic algorithms. Scientific American, 267(1), 66–73. https://doi.org/10.1038/scientificamerican0792-66
Höök, M., Xu, T., Xiongqi, P., & Aleklett, K. (2010). Development journey and outlook of Chinese giant oilfields. Petroleum Exploration and Development, 37(2), 237–249. https://doi.org/10.1016/S1876-3804(10)60029-7
K
Ki, S., Jang, I., Cha, B., Seo, J., & Kwon, O. (2020). Restoration of missing pressures in a gas well using recurrent neural networks with long short-term memory cells. Energies, 13(18), Article 4696. https://doi.org/10.3390/en13184696
Kim, J., Choe, J., & Lee, K. (2022). Sequential field development plan through robust optimization coupling with CNN and LSTM-based proxy models. Journal of Petroleum Science and Engineering, 209, Article 109887. https://doi.org/10.1016/j.petrol.2021.109887
L
Li, S., Chen, H., Wang, M., Heidari, A. A., & Mirjalili, S. (2020). Slime mould algorithm: A new method for stochastic optimization. Future Generation Computer Systems, 111, 300–323. https://doi.org/10.1016/j.future.2020.03.055
Li, X., Xiao, K., Li, X., Yu, C., Fan, D., & Sun, Z. (2022). A well rate prediction method based on LSTM algorithm considering manual operations. Journal of Petroleum Science and Engineering, 210Trace, Article 110047. https://doi.org/10.1016/j.petrol.2021.110047
Liu, W., Liu, W. D., & Gu, J. (2020). Forecasting oil production using ensemble empirical model decomposition based long short-term memory neural network. Journal of Petroleum Science and Engineering, 189, Article 107013. https://doi.org/10.1016/j.petrol.2020.107013
M
Mechanics Group, T. H. (2021). Oil production forecasting using deep learning for shale oil wells under variable gas-oil and water-oil ratios. Petroleum Science and Technology, 39(15), 1–24. https://doi.org/10.1080/10916466.2021.1953214
Maldonado-Cruz, E., & Pyrcz, M. J. (2024). Multi-horizon well performance forecasting with temporal fusion transformers. Results in Engineering, 21, Article 101776. https://doi.org/10.1016/j.rineng.2023.101776
Male, F. (2019). Using a segregated flow model to forecast production of oil, gas, and water in shale oil plays. Journal of Petroleum Science and Engineering, 180, 48–61. https://doi.org/10.1016/j.petrol.2019.05.011
Mirjalili, S. (2015). Moth-flame optimization algorithm: A novel nature-inspired heuristic paradigm. Knowledge-Based Systems, 89, 228–249. https://doi.org/10.1016/j.knosys.2015.07.006
Mirjalili, S. (2016). Dragonfly algorithm: A new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Computing and Applications, 27(4), 1053–1073. https://doi.org/10.1007/s00521-015-1920-1
Mirjalili, S. (2016). SCA: A sine cosine algorithm for solving optimization problems. Knowledge-Based Systems, 96, 120–133. https://doi.org/10.1016/j.knosys.2015.12.022
P
Pandey, R. K., Kumar, A., & Mandal, A. (2021). A robust deep structured prediction model for petroleum reservoir characterization using pressure transient test data. Petroleum Research, 6(3), 224–235. https://doi.org/10.1016/j.ptlrs.2021.03.002
R
Rezaeipour, A., Dabir, B., & Ahmadi, M. (2023). Data-driven approach to dynamic uncertainty quantification of oil well production: Decline curve analysis and hidden Markov model. Geoenergy Science and Engineering, 229, Article 212131. https://doi.org/10.1016/j.geoen.2023.212131
S
Safaei-Farouji, M., & Kadkhodaie, A. (2022). Application of ensemble machine learning methods for kerogen type estimation from petrophysical well logs. Journal of Petroleum Science and Engineering, 208, Article 109455. https://doi.org/10.1016/j.petrol.2021.109455
Sharma, N., Sharma, R., & Jindal, N. (2021). Machine learning and deep learning applications-a vision. Global Transitions Proceedings, 2(1), 24–28. https://doi.org/10.1016/j.gltp.2021.01.003
Sheikhoushaghi, A., Gharaei, N. Y., & Nikoofard, A. (2022). Application of rough neural network to forecast oil production rate of an oil field in a comparative study. Journal of Petroleum Science and Engineering, 209, Article 109935. https://doi.org/10.1016/j.petrol.2021.109935
Sircar, A., Yadav, K., Rayavarapu, K., Bist, N., & Oza, H. (2021). Application of machine learning and artificial intelligence in oil and gas industry. Petroleum Research, 6(4), 379–391. https://doi.org/10.1016/j.ptlrs.2021.05.009
T
Tang, H., Zhang, B., Liu, S., Li, H., Huo, D., & Wu, Y. S. (2021). A novel decline curve regression procedure for analyzing shale gas production. Journal of Natural Gas Science and Engineering, 88, Article 103818. https://doi.org/10.1016/j.jngse.2021.103818
Tariq, Z., Aljawad, M. S., Hasan, A., Murtaza, M., Mohammed, E., El-Husseiny, A., Alarifi, S. A., Mahmoud, M., & Abdulraheem, A. (2021). A systematic review of data science and machine learning applications to the oil and gas industry. Journal of Petroleum Exploration and Production Technology, 11(12), 4339–4374. https://doi.org/10.1007/s13202-021-01402-4
Tian, F., Lu, X., Zheng, S., Zhang, H., Rong, Y., Yang, D., & Liu, N. (2017). Structure and filling characteristics of paleokarst reservoirs in the northern Tarim basin, revealed by outcrop, core and borehole images. Open Geosciences, 9(1), 266–280. https://doi.org/10.1515/geo-2017-0022
V
Vo Thanh, H., Sugai, Y., & Sasaki, K. (2020). Application of artificial neural network for predicting the performance of CO2 enhanced oil recovery and storage in residual oil zones. Scientific Reports, 10(1), Article 18241. https://doi.org/10.1038/s41598-020-75312-3
W
Wachtmeister, H., Henke, P., & Höök, M. (2018). Oil projections in retrospect: Revisions, accuracy and current uncertainty. Applied Energy, 220Trace, 138–153. https://doi.org/10.1016/j.apenergy.2018.03.042
Wang, Q., Song, X., & Li, R. (2018). A novel hybridization of nonlinear grey model and linear ARIMA residual correction for forecasting US shale oil production. Energy, 165, 1320–1331. https://doi.org/10.1016/j.energy.2018.10.042
Wang, S., Xiang, J., Wang, X., Feng, Q., Yang, Y., Cao, X., & Hou, L. (2024). A deep learning based surrogate model for reservoir dynamic performance prediction. Geoenergy Science and Engineering, 233, Article 212516. https://doi.org/10.1016/j.geoen.2023.212516
X
Xia, L., Shun, X., Jiewen, W., & Lan, M. (2020). Predicting oil production in single well using recurrent neural network. Proceedings of the 2020 International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), 423–430. https://doi.org/10.1109/ICBAIE50303.2020.9142104
Xu, Z., & Leung, J. Y. (2024). A novel formulation of RNN-based neural network with real-time updating—An application for dynamic hydraulic fractured shale gas production forecasting. Geoenergy Science and Engineering, 233, Article 212491. https://doi.org/10.1016/j.geoen.2023.212491
Y
Yan, B., Zhong, Z., & Bai, B. (2024). A convolutional neural network-based proxy model for field production prediction and history matching. Gas Science and Engineering, 122, Article 205219. https://doi.org/10.1016/j.jgsce.2023.205219
Yehia, T., Abdelhafiz, M. M., Hegazy, G. M., Elnekhaily, S. A., & Mahmoud, O. (2023). A comprehensive review of deterministic decline curve analysis for oil and gas reservoirs. Geoenergy Science and Engineering, 226, Article 211775. https://doi.org/10.1016/j.geoen.2023.211775
Yu, C., Qu, C., & Han, J. (2017). Relationship between deep structure and oil-gas in the eastern Tarim Basin. EGU General Assembly Conference Abstracts, 19, Article 5898.
Z
Zhou, M., Li, X., Hu, Y., He, C., Guo, Q., Huang, Y., Pei, X., & Qi, N. (2024). A new evaluation method of recoverable reserves and its application in carbonate gas reservoirs. ACS Omega, 9(4), 4512–4525. https://doi.org/10.1021/acsomega.3c08112
