Optimizing oil and gas production forecasting using the subtraction-average-based optimizer
-
Tieming Zhang
and
Lihong Zhao
Abstract
The application of machine learning algorithms in forecasting oil and gas production rates is critical for optimizing resource extraction and improving operational efficiency. Accurate predictions of future production rates enable operators to maximize yields, minimize downtime, and optimize resource management. This study proposes a new evolutionary Subtraction-Average-Based Optimizer (SABO), which updates searchers’ positions in the search space using the subtraction average of searcher agents. The SABO algorithm is integrated into each machine learning model such as Decision Trees, Random Forest, Extra Trees, Adaptive Boosting, Bagging, and Categorical Boosting, for performance improvement, and the resultant hybrid models are compared and examined using the test cases of the benchmark functions and the real-world dataset. The best performance belonged to the highest R2 of 0.9327 and lowest RMSE of 2.0785 and MAE of 0.4665 for SABO-Bagging in the training set, and the test dataset recorded the best performance by the R2 of 0.9267 and lowest RMSE of 2.2157 and MAE of 0.4558. These findings indicate that the SABO-Bagging hybrid model is the best performing model for the prediction of oil and gas production rates, and it has a competitive advantage compared to other machine learning methods for operational optimization in the energy industry.
Acknowledgment
We would like to take this opportunity to acknowledge that there are no individuals or organizations that require acknowledgment for their contributions to this work.
-
Research ethics: Research involving Human Participants and Animals: The observational study conducted on medical staff needs no ethical code. Therefore, the above study was not required to acquire ethical code.
-
Informed consent: This option is not neccessary due to that the data were collected from the references.
-
Author contributions: All authors contributed to the study’s conception and design. Data collection, simulation and analysis were performed by” Tieming Zhang and Lihong Zhao”. Also, the first draft of the manuscript was written by Tieming Zhang. Lihong Zhao commented on previous versions of the manuscript.
-
Use of Large Language Models, AI and Machine Learning Tools: During the development of this work, the authors utilized Large Language Models, Artificial Intelligence, and Machine Learning tools for tasks such as language refinement, data analysis, and figure creation. All outputs generated were thoroughly reviewed and validated by the authors to ensure their accuracy and originality. The authors have reviewed and edited the content resulting from these tools/services and assume full responsibility for the final published article.
-
Conflict of interest: The authors declare no competing of interests.
-
Research funding: This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.
-
Data availability: The authors do not have permissions to share data.
References
1. Jin, M, Liao, Q, Patil, S, Abdulraheem, A, Al-Shehri, D, Glatz, G, et al.. Hyperparameter tuning of artificial neural networks for well production estimation considering the uncertainty in initialized parameters. ACS Omega 2022;7:24145–56. https://doi.org/10.1021/acsomega.2c00498.Search in Google Scholar PubMed PubMed Central
2. Ali, N, Fu, X, Chen, J, Hussain, J, Hussain, W, Rahman, N, et al.. Advancing reservoir evaluation: machine learning approaches for predicting porosity curves. Energies 2024;17:3768. https://doi.org/10.3390/en17153768.Search in Google Scholar
3. Zhang, Z. A well production prediction method based on blending heterogeneous ensemble learning optimized by OOA. Changsha, China: In: Journal of Physics: Conference Series. IOP Publishing; 2024. p. 12002.10.1088/1742-6596/2835/1/012002Search in Google Scholar
4. Box, GEP, Jenkins, GM, Reinsel, GC, Ljung, GM. Time series analysis: forecasting and control. Hoboken, New Jersey, U.S: John Wiley & Sons; 2015.Search in Google Scholar
5. Ma, X, Liu, Z. Predicting the oil production using the novel multivariate nonlinear model based on arps decline model and kernel method. Neural Comput Appl 2018;29:579–91. https://doi.org/10.1007/s00521-016-2721-x.Search in Google Scholar
6. Nasteski, V. An overview of the supervised machine learning methods. Horizons. b 2017;4:56. https://doi.org/10.20544/horizons.b.04.1.17.p05.Search in Google Scholar
7. Xing, W, Zhang, J, Li, C, Huo, Y, Dong, G. iAMP-Attenpred: a novel antimicrobial peptide predictor based on BERT feature extraction method and CNN-BiLSTM-Attention combination model. Briefings Bioinf 2024;25:bbad443. https://doi.org/10.1093/bib/bbad443.Search in Google Scholar PubMed PubMed Central
8. Wu, T, Fang, H, Sun, H, Zhang, F, Wang, X, Wang, Y, et al.. A data-driven approach to evaluate fracturing practice in tight sandstone in changqing field. In: International Petroleum Technology Conference, IPTC; 2021. D071S024R002.10.2523/IPTC-21821-MSSearch in Google Scholar
9. Han, D, Jung, J, Kwon, S. Comparative study on supervised learning models for productivity forecasting of shale reservoirs based on a data-driven approach. Appl Sci 2020;10:1267. https://doi.org/10.3390/app10041267.Search in Google Scholar
10. Šapina, M. Usporedba karata dubina dobivenih metodom umjetnih neuronskih mreža I običnim krigiranjem U donjemu I gornjemu panonu unutar bjelovarske subdepresije U sjevernoj hrvatskoj. Rudarsko-Geolosko-Naftni Zb 2016;31:75–85.10.17794/rgn.2016.3.6Search in Google Scholar
11. Abdullayeva, F, Imamverdiyev, Y. Development of oil production forecasting method based on deep learning. Statistics, Optimization Inf Comput 2019;7:826–39. https://doi.org/10.19139/soic-2310-5070-651.Search in Google Scholar
12. Chen, G, Tian, H, Xiao, T, Xu, T, Lei, H. Time series forecasting of oil production in enhanced oil recovery system based on a novel CNN-GRU neural network. Geoenergy Sci Eng 2024;233:212528. https://doi.org/10.1016/j.geoen.2023.212528.Search in Google Scholar
13. Ning, Y, Kazemi, H, Tahmasebi, P. A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and prophet. Comput Geosci 2022;164:105126. https://doi.org/10.1016/j.cageo.2022.105126.Search in Google Scholar
14. Sagheer, A, Kotb, M. Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing 2019;323:203–13. https://doi.org/10.1016/j.neucom.2018.09.082.Search in Google Scholar
15. Avula, VR, Kapavarapu, BB, Chandran, A, Balagopalan, A, Naik, MS. Prediction of oil production using optimized gated recurrent unit (GRU). Chennai, India: 2024 International Conference on Recent Advances in Electrical. In: Electronics, Ubiquitous Communication, and Computational Intelligence. IEEE; 2024:1–6 pp.10.1109/RAEEUCCI61380.2024.10547901Search in Google Scholar
16. Ma, X, Zhang, L, Zhan, J, Chang, S. Application of dual-stage attention temporal convolutional networks in gas well production prediction. Mathematics 2024;12:3896. https://doi.org/10.3390/math12243896.Search in Google Scholar
17. Zhen, Y, Fang, J, Zhao, X, Ge, J, Xiao, Y. Temporal convolution network based on attention mechanism for well production prediction. J Pet Sci Eng 2022;218:111043. https://doi.org/10.1016/j.petrol.2022.111043.Search in Google Scholar
18. Wang, M, Hui, G, Pang, Y, Wang, S, Chen, S. Optimization of machine learning approaches for shale gas production forecast. Geoenergy Sci Eng 2023;226:211719. https://doi.org/10.1016/j.geoen.2023.211719.Search in Google Scholar
19. Omotosho, TJ. Oil production prediction using time series forecasting and machine learning techniques. In: SPE Nigeria Annual International Conference and Exhibition, SPE; 2024. D032S028R006.10.2118/221728-MSSearch in Google Scholar
20. Nemer, ZN, N Nemer, Z. Oil and gas production forecasting using decision trees, random forst, and XGBoost. J Al-Qadisiyah Comput Sci Math 2024;16:9–20. https://doi.org/10.29304/jqcsm.2024.16.11431.Search in Google Scholar
21. Bassey, M, Akpabio, MG, Agwu, OE. Enhancing natural gas production prediction using machine learning techniques: a study with random forest and artificial neural network models. In: SPE Nigeria Annual International Conference and Exhibition, SPE; 2024. D021S010R004.10.2118/221577-MSSearch in Google Scholar
22. Liao, L, Zeng, Y, Liang, Y, Zhang, H. Data mining: a novel strategy for production forecast in tight hydrocarbon resource in Canada by random forest analysis. In: International petroleum technology conference, IPTC; 2020. D031S085R001.10.2523/IPTC-20344-MSSearch in Google Scholar
23. Laib, O, Khadir, MT, Mihaylova, L. A Gaussian process regression for natural gas consumption prediction based on time series data. Cambridge, UK: In: 2018 21st International Conference on Information Fusion (FUSION). IEEE; 2018:55–61.10.23919/ICIF.2018.8455447Search in Google Scholar
24. Van Hung, N, Loc, LK, Huong, NTT, Van Dung, N, Quy, NM. Applied machine learning and deep learning to predict oil and gas production. Chi Minh City, Vietnam. In: Vietnam Symposium on Advances in Offshore Engineering. Springer; 2021:451–8 pp.10.1007/978-981-16-7735-9_50Search in Google Scholar
25. de Oliveira Werneck, R, Prates, R, Moura, R, Gonçalves, MM, Castro, M, Soriano-Vargas, A, et al.. Data-driven deep-learning forecasting for oil production and pressure. J Pet Sci Eng 2022;210:109937. https://doi.org/10.1016/j.petrol.2021.109937.Search in Google Scholar
26. Fan, Z, Liu, X, Wang, Z, Liu, P, Wang, Y. A novel ensemble machine learning model for oil production prediction with two-stage data preprocessing. Processes 2024;12:587. https://doi.org/10.3390/pr12030587.Search in Google Scholar
27. Shittu, IA, Arifalo, E. Data driven approach for predicting natural gas outputs from unconventional oil fields using machine learning techniques. In: SPE Nigeria Annual International Conference and Exhibition, SPE; 2025. D032S028R005.10.2118/228744-MSSearch in Google Scholar
28. Meng, X, Liu, X, Duan, H, Hu, Z, Wang, M. Optimization of oil well production prediction model based on inter-attention and BiLSTM. Electronics (Basel) 2025;14:1004. https://doi.org/10.3390/electronics14051004.Search in Google Scholar
29. Dogru, N, Subasi, A. Traffic accident detection using random forest classifier. Jeddah, Saudi Arabia: In: 2018 15th Learning and Technology Conference (L&T). IEEE; 2018. pp. 40–5.10.1109/LT.2018.8368509Search in Google Scholar
30. Shah, K, Patel, H, Sanghvi, D, Shah, M. A comparative analysis of logistic regression, random forest and KNN models for the text classification. Augmented Human Research 2020;5:12. https://doi.org/10.1007/s41133-020-00032-0.Search in Google Scholar
31. Samsami, MM, Yasrebi, N. Novel RFID anti-collision algorithm based on the Monte–Carlo query tree search. Wirel Netw 2021;27:621–34. https://doi.org/10.1007/s11276-020-02466-1.Search in Google Scholar
32. Livingston, F. Implementation of Breiman’s random forest machine learning algorithm. ECE591Q Mach Learn J Pap 2005:1–13.Search in Google Scholar
33. Trojovský, P, Dehghani, M. Subtraction-average-based optimizer: a new swarm-inspired metaheuristic algorithm for solving optimization problems. Biomimetics 2023;8:149. https://doi.org/10.3390/biomimetics8020149.Search in Google Scholar PubMed PubMed Central
34. Jebli, I, Belouadha, FZ, Kabbaj, MI, Tilioua, A. Prediction of solar energy guided by pearson correlation using machine learning. Energy 2021;224. https://doi.org/10.1016/j.energy.2021.120109.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
