A Hybrid Transfer Learning Framework for Enhanced Oil Production Time Series Forecasting
DOI:
https://doi.org/10.32604/cmc.2025.059869الكلمات المفتاحية:
Time series forecastingg; aussian transformation ;quantile transformation; long short-term memory; gated recurrent unitsالملخص
Accurate forecasting of oil production is essential for optimizing resource management and minimizing operational risks in the energy sector. Traditional time-series forecasting techniques, despite their widespread application, often encounter difficulties in handling the complexities of oil production data, which is characterized by non-linear patterns, skewed distributions, and the presence of outliers. To overcome these limitations, deep learning methods have emerged as more robust alternatives. However, while deep neural networks offer improved accuracy, they demand substantial amounts of data for effective training. Conversely, shallow networks with fewer layers lack the capacity to model complex data distributions adequately. To address these challenges, this study introduces a novel hybrid model called Transfer LSTM to GRU (TLTG), which combines the strengths of deep and shallow networks using transfer learning. The TLTG model integrates Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRU) to enhance predictive accuracy while maintaining computational efficiency. Gaussian transformation is applied to the input data to reduce outliers and skewness, creating a more normal-like distribution. The proposed approach is validated on datasets from various wells in the Tahe oil field, China. Experimental results highlight the superior performance of the TLTG model, achieving 100% accuracy and faster prediction times (200 s) compared to eight other approaches, demonstrating its effectiveness and efficiency.
المراجع
1. F Male, "Using a segregated flow model to forecast production of oil, gas, and water in shale oil plays," J Pet Sci Eng, vol. 180, no. 9, pp. 48-61, 2019.
2. W Liu, WD Liu, J Gu, "Forecasting oil production using ensemble empirical model decomposition based Long Short-Term Memory neural network," J Pet Sci Eng, vol. 189, no. 2, p. 107013, 2020.
3. S Bhardwaj, E Chandrasekhar, P Padiyar, VM Gadre, "A comparative study of wavelet-based ANN and classical techniques for geophysical time-series forecasting," Comput Geosci, vol. 138, no. 1, p. 104461, 2020.
4. D AL-Alimi, AM AlRassas, MAA Al-qaness, Z Cai, AO Aseeri, M Abd Elaziz, "TLIA: time-series forecasting model using long short-term memory integrated with artificial neural networks for volatile energy markets," Appl Energy, vol. 343, no. 7, p. 121230, 2023.
5. A Sagheer, M Kotb, "Time series forecasting of petroleum production using deep LSTM recurrent networks," Neurocomputing, vol. 323, no. 3, pp. 203-213, 2019.
6. H Abbasimehr, A Behboodi, A Bahrini, "A novel hybrid model to forecast seasonal and chaotic time series," Expert Syst Appl, vol. 239, no. 1, p. 122461, 2024.
7. CR Clarkson, JD Williams-Kovacs, F Qanbari, H Behmanesh, MH Sureshjani, "History-matching and forecasting tight/shale gas condensate wells using combined analytical, semi-analytical, and empirical methods," J Nat Gas Sci Eng, vol. 26, pp. 1620-1647, 2015.
8. S Kalra, W Tian, X Wu, "A numerical simulation study of CO2 injection for enhancing hydrocarbon recovery and sequestration in liquid-rich shales," Pet Sci, vol. 15, pp. 103-115, 2018.
9. X Song, Y Liu, L Xue, J Wang, J Zhang, J Wang, "Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model," J Pet Sci Eng, vol. 186, no. 2, p. 106682, 2020.
10. A Tealab, "Time series forecasting using artificial neural networks methodologies: a systematic review," Futur Comput Informatics J, vol. 3, no. 2, pp. 334-340, 2018.
11. Z Zhang, JC Moore, "Mathematical and physical fundamentals of climate change," in Mathematical and physical fundamentals of climate change, Elsevier, Boston, pp. 239-290, 2015.
12. Y Ning, H Kazemi, P Tahmasebi, "A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet," Comput Geosci, vol. 164, no. 1, p. 105126, 2022.
13. Y Eren, İ Küçükdemiral, "A comprehensive review on deep learning approaches for short-term load forecasting," Renew Sustain Energy Rev, vol. 189, no. 1, p. 114031, 2024.
14. Y LeCun, Y Bengio, G Hinton, "Deep learning," Nature, vol. 521, pp. 436-444, 2015.
15. SA Edalatpanah, FS Hassani, F Smarandache, A Sorourkhah, D Pamucar, B Cui, "A hybrid time series forecasting method based on neutrosophic logic with applications in financial issues," Eng Appl Artif Intell, vol. 129, no. 2, p. 107531, 2024.
16. N Bacanin, C Stoean, M Zivkovic, M Rakic, R Strulak-Wójcikiewicz, R Stoean, "On the benefits of using metaheuristics in the hyperparameter tuning of deep learning models for energy load forecasting," Energies, vol. 16, no. 3, p. 1434, 2023.
17. J Wang, J Cao, S Yuan, "Shear wave velocity prediction based on adaptive particle swarm optimization optimized recurrent neural network," J Pet Sci Eng, vol. 194, no. 5, p. 107466, 2020.
18. NO Nikitin, I Revin, A Hvatov, P Vychuzhanin, AV Kalyuzhnaya, "Hybrid and automated machine learning approaches for oil fields development: the case study of Volve field, North Sea," Comput Geosci, vol. 161, no. 4, p. 105061, 2022.
19. J Lu, V Behbood, P Hao, H Zuo, S Xue, G Zhang, "Transfer learning using computational intelligence: a survey," Knowl-Based Syst, vol. 80, pp. 14-23, 2015.
20. T Le, MT Vo, T Kieu, E Hwang, S Rho, SW Baik, "Multiple electric energy consumption forecasting using a cluster-based strategy for transfer learning in smart building," Sensors, vol. 20, no. 9, p. 2668, 2020.
21. R Ye, Q Dai, "A novel transfer learning framework for time series forecasting," Knowl-Based Syst, vol. 156, no. 6, pp. 74-99, 2018.
22. B Liang, J Liu, J You, J Jia, Y Pan, H Jeong, "Hydrocarbon production dynamics forecasting using machine learning: a state-of-the-art review," Fuel, vol. 337, no. 6, p. 127067, 2023.
23. A Fernández, S García, M Galar, RC Prati, B Krawczyk, F Herrera, "Learning from imbalanced data sets," in Learning from imbalanced data sets, Springer International Publishing, Cham, 2018.
24. VNG Raju, KP Lakshmi, VM Jain, A Kalidindi, V Padma, "Study the influence of normalization/transformation process on the accuracy of supervised classification," pp. 729-735, Aug. 20-22, 2020.
25. K Cho, B Van Merriënboer, C Gulcehre, D Bahdanau, F Bougares, H Schwenk, "Learning phrase representations using RNN encoder-decoder for statistical machine translation," 2014.
26. AM AlRassas, MAA Al-qaness, AA Ewees, S Ren, M Abd Elaziz, R Damaševičius, "Optimized ANFIS model using aquila optimizer for oil production forecasting," Processes, vol. 9, no. 7, p. 1194, 2021.
27. A Alalimi, L Pan, MAA Al-qaness, AA Ewees, X Wang, M Abd Elaziz, "Optimized random vector functional link network to predict oil production from tahe oil field in China," Oil Gas Sci Technol-Rev IFP Energies Nouv, vol. 76, no. 3, pp. 1-10, 2021.
28. MK Shende, SQ Salih, ND Bokde, M Scholz, AY Oudah, ZM Yaseen, "Natural time series parameters forecasting: validation of the pattern-sequence-based forecasting (PSF) algorithm; a new python package," Appl Sci, vol. 12, no. 12, p. 6194, 2022.
29. H Kokko, "Who is afraid of modelling time as a continuous variable?," Methods Ecol Evol, vol. 15, no. 10, pp. 1736-1756, 2024.
30. ND Bokde, B Tranberg, GB Andresen, "Short-term CO2 emissions forecasting based on decomposition approaches and its impact on electricity market scheduling," Appl Energy, vol. 281, p. 116061, 2020.
31. ZI Erzurum Cicek, Z Kamisli Ozturk, "Optimizing the artificial neural network parameters using a biased random key genetic algorithm for time series forecasting," Appl Soft Comput, vol. 102, no. 6, p. 107091, 2021.
32. U Iturrarán-Viveros, JO Parra, "Artificial Neural Networks applied to estimate permeability, porosity and intrinsic attenuation using seismic attributes and well-log data," J Appl Geophys, vol. 107, no. 5, pp. 45-54, 2014.
33. AB Zolotukhin, AT Gayubov, "Machine learning in reservoir permeability prediction and modelling of fluid flow in porous media," IOP Conf Ser: Mater Sci Eng, vol. 700, no. 1, p. 012023, 2019.
34. WJ Al-Mudhafar, "Integrating well log interpretations for lithofacies classification and permeability modeling through advanced machine learning algorithms," J Pet Explor Prod Technol, vol. 7, no. 4, pp. 1023-1033, 2017.
التنزيلات
منشور
إصدار
القسم
الرخصة
الحقوق الفكرية (c) 2025 CC BY 4.0
هذا العمل مرخص بموجب Creative Commons Attribution 4.0 International License.
