Mohammad Lutfi; Muh. Yamin; Mujibu Rahman

Python–based Hybrid Decline Curve–Machine Learning Model for Forecasting Oil Production and Deriving CO₂ Emission Potential from Estimated Remaining Reserves

PDF (1216KB), PP.14-26

Views: 0 Downloads: 0

Author(s)

Mohammad Lutfi ^1,* Muh. Yamin ² Mujibu Rahman ²

1. Department of Petroleum Engineering, STT Migas, Balikpapan, 76127, Indonesia

2. State Agricultural Polytechnic of Samarinda, Samarinda, 75131, Indonesia

* Corresponding author.

DOI: https://doi.org/10.5815/ijieeb.2026.05.02

Received: 24 Nov. 2025 / Revised: 17 Dec. 2025 / Accepted: 2 Feb. 2026 / Published: 8 Oct. 2026

Index Terms

Decline Curve Analysis (DCA), Machine Learning, Support Vector Regression (SVR), CO₂ Emission Estimation, Production Forecasting.

Abstract

This study develops a Python-based hybrid forecasting framework that integrates classical Decline Curve Analysis (DCA) with Support Vector Regression (SVR) to improve the reliability of oil production forecasting and the estimation of Estimated Remaining Reserves (ERR), which are subsequently used to derive cumulative CO₂ emission potential. Historical production data are segmented to represent boundary-dominated flow conditions, enhancing the stability and physical consistency of decline parameters. SVR is then applied to correct localized deviations in the historical response that are not captured by conventional DCA formulations, yielding improved decline representations for forecasting. The hybrid DCA–SVR model achieves a more coherent historical match and reduced average residual errors compared to standalone exponential, hyperbolic, and harmonic decline models. Using the hybrid framework, ERR estimates of 4.92×10⁵, 1.74×10⁶, and 3.62×10⁶ STB were obtained for the exponential, hyperbolic, and harmonic decline scenarios, respectively, corresponding to cumulative CO₂ emission potentials of approximately 213,036, 753,420, and 1,567,460 tons of CO₂. These scenario-based results provide a bounded range of emission outcomes, explicitly demonstrating that uncertainty in decline model selection propagates directly into long-term ERR and CO₂ emission estimates. Overall, the proposed hybrid machine learning–decline curve analysis (ML-DCA) framework offers a transparent and reproducible approach for linking production forecasting with quantitative CO₂ impact assessment in data-driven reservoir management.

Cite This Paper

Mohammad Lutfi, Muh. Yamin, Mujibu Rahman, "Python–based Hybrid Decline Curve–Machine Learning Model for Forecasting Oil Production and Deriving CO₂ Emission Potential from Estimated Remaining Reserves", International Journal of Information Engineering and Electronic Business(IJIEEB), Vol.18, No.5, pp. 14-26, 2026. DOI:10.5815/ijieeb.2026.05.02

Reference

[1]H. Zhang, D. Rietz, A. Cagle, M. Cocco, and J. Lee, “Extended exponential decline curve analysis,” Journal of Natural Gas Science and Engineering, vol. 36, pp. 402–413, 2016.
[2]T. Yehia, M. M. Abdelhafiz, G. M. Hegazy, S. A. Elnekhaily, and O. Mahmoud, “A comprehensive review of deterministic decline curve analysis for oil and gas reservoirs,” Geoenergy Science and Engineering, vol. 226, p. 211775, 2023.
[3]R. Zhu et al., “Well-production forecasting using machine learning with feature selection and automatic hyperparameter optimization,” Energies, vol. 18, no. 1, p. 99, 2024.
[4]P. Manda and D. B. Nkazi, “The evaluation and sensitivity of decline curve modelling,” Energies, vol. 13, no. 11, p. 2765, 2020.
[5]A. Hong, R. B. Bratvold, L. W. Lake, and L. M. Ruiz Maraggi, “Integrating model uncertainty in probabilistic decline-curve analysis for unconventional-oil-production forecasting,” SPE Reservoir Evaluation & Engineering, vol. 22, no. 03, pp. 861–876, 2019.
[6]B. Sulaiman, A. N. Bambang, H. Purnaweni, M. Lutfi, and E. M. A. Mohammed, “Coastal community perception of mangroves in Suli subdistrict, Luwu,” Jurnal Pendidikan IPA Indonesia, vol. 8, pp. 561–569, 2019.
[7]M. S. Masnadi et al., “Global carbon intensity of crude oil production,” Science, vol. 361, no. 6405, pp. 851–853, 2018.
[8]D. Shapovalova, “Climate change and oil and gas production regulation: an impossible reconciliation?” Journal of International Economic Law, vol. 26, no. 4, pp. 817–835, 2023.
[9]S. K. Chrysikopoulos et al., “Decarbonization in the Oil and Gas Sector: The Role of Power Purchase Agreements and Renewable Energy Certificates,” Sustainability, vol. 16, no. 15, 2024.
[10]M. Lutfi, “Hydrodynamics circulation model in the estuary of Palu River based on numerical calculations,” Journal of Engineering Science and Technology, vol. 15, pp. 2309–2323, 2020.
[11]M. Lutfi, “Insight of numerical simulation for current circulation on the steep slopes of bathymetry and topography in Palu Bay, Indonesia,” Fluids, vol. 6, p. 234, 2021.
[12]M. Lutfi, “Three-dimensional numerical modeling of current and temperature distribution in the estuary of Palu River,” Journal of Physics: Conference Series, vol. 1354, no. 1, p. 012020, Oct. 2019.
[13]A. M. Wahba, H. M. Khattab, M. A. Tantawy, and A. A. Gawish, “Modern decline curve analysis of unconventional reservoirs: a comparative study using actual data,” Journal of Petroleum and Mining Engineering, vol. 24, no. 1, pp. 51–65, 2022.
[14]H. Alimohammadi and S. N. Chen, “Long-term production forecast in tight and shale reservoirs: Adapting probability density functions for decline curve analysis,” Gas Science and Engineering, vol. 118, p. 205113, 2023.
[15]Y. Zhou et al., “An Improved Decline Curve Analysis Method via Ensemble Learning for Shale Gas Reservoirs,” Energies, vol. 17, no. 23, p. 5910, 2024.
[16]W. Liu, Z. Chen, Y. Hu, and L. Xu, “A systematic machine learning method for reservoir identification and production prediction,” Petroleum Science, vol. 20, no. 1, pp. 295–308, 2023.
[17]A. Samnioti and V. Gaganis, “Applications of machine learning in subsurface reservoir simulation—A review—Part II,” Energies, vol. 16, no. 18, p. 6727, 2023.
[18]S. Wen et al., “Forecasting oil production in unconventional reservoirs using long short term memory network coupled support vector regression method: A case study,” Petroleum, vol. 9, no. 4, pp. 647–657, 2023.
[19]X. Ma, M. Hou, J. Zhan, and R. Zhong, “Enhancing production prediction in shale gas reservoirs using a hybrid gated recurrent unit and multilayer perceptron (GRU-MLP) model,” Applied Sciences, vol. 13, no. 17, p. 9827, 2023.
[20]H. Rahmanifard and I. Gates, “A comprehensive review of data-driven approaches for forecasting production from unconventional reservoirs: best practices and future directions,” Artificial Intelligence Review, vol. 57, no. 8, p. 213, 2024.
[21]C. Zhang and X. Zhou, “Forecasting value-at-risk of crude oil futures using a hybrid ARIMA-SVR-POT model,” Heliyon, vol. 10, no. 1, 2024.
[22]M. Lutfi, “The effect of gravitational field on brachistochrone problem,” Journal of Physics: Conference Series, vol. 1028, p. 012060, 2018.
[23]J. Chahar, J. Verma, D. Vyas, and M. Goyal, “Data-driven approach for hydrocarbon production forecasting using machine learning techniques,” Journal of Petroleum Science and Engineering, vol. 217, p. 110757, 2022.
[24]A. Muliawan, M. Sali, and M. Lutfi, “XRD and XRF characterization of white sand from Sambera Village, East Kalimantan, Indonesia,” Journal of Physics: Conference Series, vol. 1242, no. 1, p. 012029, 2019.
[25]M. Nagao, A. Datta-Gupta, T. Onishi, and S. Sankaran, “Physics informed machine learning for reservoir connectivity identification and robust production forecasting,” SPE Journal, vol. 29, no. 09, pp. 4527–4541, 2024.
[26]J. Foster, S. Misra, O. Osogba, and M. Bhatia, “Machine learning assisted detection of excess water-producing wells in unconventional shale plays,” Journal of Natural Gas Science and Engineering, vol. 92, p. 104025, 2021.
[27]Y. Li and Y. Han, “Decline curve analysis for production forecasting based on machine learning,” SPE Symposium: Production Enhancement and Cost Optimisation, p. D011S004R003, 2017.
[28]G. M. Mask, X. Wu, and C. Nicholson, “Enhanced hydrocarbon production forecasting combining machine learning, transfer learning, and decline curve analysis,” Gas Science and Engineering, vol. 134, p. 205522, 2025.
[29]X. Li et al., “Hybrid Data-Driven and Physics-Based Forecasting Models for Shale Wells,” 2020.
[30]N. Ferreira et al., “Introduction of a carbon footprint assessment in the oil and gas facility life extension decision-making process,” Geoenergy Science and Engineering, vol. 240, p. 213032, 2024.
[31]I. V. den Bijgaart and M. Rodriguez, “Closing wells; fossil exploration and abandonment in the energy transition,” 2020.
[32]K. M. Parker and M. R. Mainelli, “What happens if we ‘burn all the carbon’? carbon reserves, carbon budgets, and policy options for governments,” Environmental Science: Atmospheres, vol. 4, no. 4, pp. 435–454, 2024.
[33]IPCC, 2019 Refinement to the 2006 IPCC Guidelines for National Greenhouse Gas Inventories, 2019.
[34]Y. F. Nassar et al., “Estimation of CO₂ emission factor for the energy industry sector in Libya: a case study,” Environment, Development and Sustainability, vol. 23, no. 9, pp. 13998–14026, 2021.
[35]Y. Tao et al., “A hybrid scenario analysis for the selection of future greenhouse gas emissions reduction technologies in China’s oil and gas industry,” Journal of Cleaner Production, vol. 223, pp. 14–24, 2019.
[36]Equinor. (n.d.). Volve data sharing. Retrieved December 19, 2025, from https://www.equinor.com/energy/volve-data-sharing
[37]Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principles and Practice (3rd ed.). OTexts.
[38]J. J. Arps, “Analysis of Decline Curves,” Transactions of the AIME, 1945.
[39]Y. J. Tawfeeq, Q. A. A. Aziz, and A. H. Al-Hadidy, “Prediction of wells performance and producing life applying production decline analysis,” The Iraqi Geological Journal, pp. 111–120, 2024.
[40]S. Al-Rbeawi, F. S. Kadhim, and J. Owayed, “New approach for decline curve analysis of unconventional fractured reservoirs: Rate-normalized flow rate derivative concept,” Journal of Energy Sustainability and Economics, vol. 1, no. 1, pp. 25–51, 2025.
[41]Rukmana, D., Kristanto, D., & Aji, V. D. C. (2012). Teknik reservoir: teori dan aplikasi. Pohon Cahaya.
[42]Okotie, S., & Ikporo, B. (2019). Reservoir engineering: principles and applications. Springer, Berlin–Heidelberg, Germany.
[43]H. Abdul Rahman, A. A. Noraidi, A. N. Hj Khalid, A. Z. Mohamad-Adam, N. H. Zahari, and N. E. Tuming, “Practical guide to calculate sample size for chi-square test in biomedical research,” BMC Medical Research Methodology, vol. 25, p. 144, 2025.
[44]Drucker, H., Burges, C. J. C., Kaufman, L., Smola, A. J., & Vapnik, V. N. (1997). Support vector regression machines. Advances in Neural Information Processing Systems, 9, 155–161.
[45]Chalimourda, A., Schölkopf, B., & Smola, A. J. (2004). Experimentally optimal ν in support vector regression for different noise models and parameter settings. Neural Networks, 17(1), 127-141.
[46]Ngo, H. H., Pham, H. D., Nguyen, N. T., Hoang, K. S., Tran, N. T., & Tran, V. T. (2024). Application of machine learning to decline curve analysis (DCA) for gas-condensate production wells with complex production history due to add-on perforation of new reservoirs. Petrovietnam Journal, 1, 51-57. https://doi.org/10.47800/PVSI.2024.01-06
[47]Li, W., Dong, Z., Lee, J. W., Ma, X., & Qian, S. (2022). Development of Decline Curve Analysis Parameters for Tight Oil Wells Using a Machine Learning Algorithm. Geofluids.
[48]Vapnik, V. N. (1995). The nature of statistical learning theory. Springer.
[49]Fetkovich, M. J. (1973, September). Decline curve analysis using type curves. In SPE Annual Technical Conference and Exhibition (pp. SPE-4629). SPE.
[50]Dake, L. P. (1983). Fundamentals of reservoir engineering (Vol. 8). Elsevier.
[51]Chapra, S. C., & Canale, R. P. Numerical Methods for Engineers, 7th ed. New York: McGraw-Hill, 2015.
[52]U.S. Environmental Protection Agency. (2024). GHG emission factors hub. https://www.epa.gov/climateleadership/ghg-emission-factors-hub, Accessed November 23, 2025
[53]U.S. Energy Information Administration. (2024). Carbon dioxide emissions coefficients by fuel. https://www.eia.gov/environment/emissions/co2_vol_mass.php, Accessed November 23, 2025
[54]Ahmed, T. (2019). Reservoir Engineering Handbook (5th ed.). Gulf Professional Publishing (Elsevier).
[55]Sun, Q., Dai, C., Wang, X., Feng, Q., Zhao, Q., Yan, C., Xu, L., & Yuan, M. (2024). Review about evaluation methods of recoverable reserves of deep water drive gas reservoirs in China. Frontiers in Energy Research, 12, 1403259.
[56]Al Lawati, J. (2024). Maximizing Estimated Ultimate Recovery from Unconventional Gas Reservoirs: A Decline Curve Analysis Approach. International Journal of Earth Sciences Knowledge and Applications, 6(3), 271-281.
[57]Tan, L., Zuo, L., & Wang, B. (2018). Methods of Decline Curve Analysis for Shale Gas Reservoirs. Energies 11 (3): 552.
[58]Mahadik, M. K. H., Bahrami, H., Hossain, M., & Mitchel, T. (2012). Production decline analysis and forecasting in tight-gas reservoirs. The APPEA Journal, 52(1), 573-580.
[59]H. Jahediesfanjani, “Application of decline curve analysis to estimate recovery factors for carbon dioxide enhanced oil recovery,” U.S. Geological Survey, Scientific Investigations Report 2017-5062-C, 2017.
[60]K. Aleklett, “Reserve driven forecasts for oil, gas, coal and limits in carbon dioxide emissions,” Proceedings of the International Transport Forum, pp. 1–20, 2007.

International Journal of Information Engineering and Electronic Business (IJIEEB)