Multiple Linear Regression Models for Crude Oil Forecasting in the A-NC115 Field, Libya

Abdulkader Fauzi Aissa Alagili

doi:10.65540/wfrjkt63

المؤلفون

abdulkader alagili Akakus oil operation company

DOI:

https://doi.org/10.65540/wfrjkt63

الكلمات المفتاحية:

El-sharara A-NC115 Libyan oilfield، Multiple Linear Regression، Oil Production Forecasting Model

الملخص

Accurate multi-horizon production forecasting remains a critical challenge in mature Libyan oilfields. In this paper, a Multiple Linear Regression (MLR) approach is proposed to forecast crude oil production in the A-NC115 oilfield, Libya, by identifying the main influencing variables. Unlike most previous studies conducted in Nigerian and other international fields, this study applies MLR forecasting to a mature Libyan oilfield, addressing an important regional research gap. The A-NC115 field is a mature water-supported reservoir where accurate forecasting of oil production is of essential importance. The trends of production, pressure, and water injection directly impact the operational and development decisions. the three different models were developed and evaluated: a short-term model based on daily data, a mid-term model based on monthly data and a long-term model based on yearly data. Historical production data from February 2018 to December 2023 was collected, pre-processed and analyzed using Minitab software. Model performance was evaluated on a hold-out testing dataset (Jan 2024 - Apr 2024) using statistical metrics such as R-squared (R²), Adjusted R², Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The best accuracy was achieved for the daily model (R²= 99.99%, MAPE = 7.20%) followed by the yearly model (R²= 99.84%, MAPE = 8.67%). The monthly model is still quite explanatory (R²= 99.96%) but with a higher MAPE (17.87%) showing a higher variance of prediction at this specific temporal scale. The results suggest that data-driven models provide accurate forecasts that support improved resource management, maintenance planning, and more efficient operational and strategic decision-making, along with a better understanding of future needs such as equipment upgrades, associated water management, and production optimization.

التنزيلات

تنزيل البيانات ليس متاحًا بعد.

المراجع

[1] Oladeinde, M. H., Ohwo, A. O., & Oladeinde, C. A. (2015). A mathematical model for predicting output in an oilfield in the Niger Delta Area of Nigeria. Nigerian Journal of Technology,34(4), pp768-772. https:// doi.org/10.4314/njt.v34i4.14

[2] Mustafar, I. (2011). A research on prediction of output in oilfield using multiple linear regression. Perak, Malaysia: International Journal of Applied Science and Technology Vol. 1 No.4.

[3] Madhukumar, M., Sebastian, A., Liang, X., Jamil, M., & Shabbir, M. N. S. K. (2022). Regression model-based short-term load forecasting for university campus load. IEEE Access, 10, pp. 8891-8905. https:// doi.org/10.1109/access.2022.3144206

[4] AlRassas, A. M., Al-qaness, M. A., Ewees, A. A., Ren, S., Abd Elaziz, M., Damaševičius, R., & Krilavičius, T. (2021). Optimized ANFIS model using Aquila Optimizer for oil production forecasting. Processes, 9(7), p. 1194. https://doi.org/10.3390/pr9071194

[5] Zhu, C., & Zhao, X. (2009). Application of Artificial Neural Network in the Prediction of Output in Oilfield. International Joint Conference on Artificial Intelligence. https:// doi.org/10.1109/jcai.2009.93

[6] Study by Guo, L., & Deng, X. (2009) entitled "Application of improved multiple linear regression method in oilfield output forecasting". In 2009 International conference on information management, innovation management and industrial engineering Vol. 1, pp. 133-136. https://doi.org/10.1109/iciii.2009.39

[7] Akukas Oil Operations Company. (2023). All Field data and maps related to El Sharara oil field, Al-Tahadi Street, Airport Road, Tripoli, Libya.

[8] Izni, G.M. and Radzuan, R. (2011). A Study on Prediction of Output in Oilfield Using Multiple Linear Regressions. International Journal of Applied Science and Technology, vol. 1, no. 4, pp. 21-27.

[9] Yale University. (1997). Multiple Linear Regression. Retrieved September 19, 2010, Available: https://www.stat.yale.edu/Courses/1997-98/101/anovareg.htm#mult

[10] Sun, Y., Wang, X., Zhang, C., & Zuo, M. (2023). Multiple Regression: Methodology and Applications. Highlights in Science, Engineering and Technology, 49, pp. 542-548. https://doi.org/10.54097/hset.v49i.8611

[11] Alin, A. (2010). Minitab. Wiley interdisciplinary reviews: computational statistics, 2(6), pp. 723-727. https://doi.org/10.1002/wics.113

[12] Hosseini, S., & Akilan, T. (2023) 'Advance deep regression models for forecasting time series oil production' arXiv preprint arXiv:2308.16105. https://doi.org/10.48550/arXiv.2308.16105

[13] AlRassas, A. M., Al-Qaness, M. A., Ewees, A. A., Ren, S., Sun, R., Pan, L., & Abd Elaziz, M. (2022) entitled 'Advance artificial time series forecasting model for oil production using neuro fuzzy-based slime mould algorithm', Journal of Petroleum Exploration and Production Technology, pp. 1-13. https://doi.org/10.1007/s13202-021-01405-w

[14] Kutner, M. H., Nachtsheim, C. J., & Neter, J. (2004). Applied linear regression models (4th ed.). New York: McGraw-Hill/Irwin.

[15] Ifowodo, H. F., Chinwuko, E. C., & Mgbemena, C. O. (2020) "Forecast of Crude Oil Production Output in An Oil Field in the Niger Delta Region of Nigeria". International Journal of Industrial Engineering, 31(1), pp.161-170. https://doi.org/10.22068/IJIEPR.31.1.161

[16] Study by Ruiz, M., Espinosa, G. A., Obando, A., & Alvarez, H. (2019) "Combined artificial intelligence modeling for production forecast in an oil field" CT&F-Ciencia, tecnología y futuro,9(1)، pp.27-35. https://doi.org/10.29047/01225383.149

[17] Study by Aydin, G.Ö.K.H.A.N. (2015) Regression models for forecasting global oil production", Petroleum Science and Technology, 33(21-22), pp. 1822-1828.https://doi.org/10.1080/10916466.2015.1101474

[18] Lewis, C. D. (1982). Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting. Butterworth Scientific. https://doi.org/10.1002/for.3980020210

[19] U.S. Energy Information Administration (2024). Country Analysis Brief: Libya, www.eia.gov U.S. Department of Energy Washington, DC 20585.

[20] Pärt-Enander, E., & Sjöberg, A. (1999). The MATLAB 5 handbook (2nd ed.). Reading, MA: Addison-Wesley Longman.

[21] Wang, J. (1993). A theoretical discussion of production decline curve of oil and gas reservoirs. Petroleum Exploration and Development, China.

[22] Wang, T., Chen, X. G., & Li, Y. F. (2006). Optimization of multivariate model in oilfield output prediction. Computer Simulation, New York.

[23] Sokolov, S., (2016). Mathematical prediction model for base oil production with account of uncertainties based on the method of displacement characteristics. Tyumen State Univ. Herald. Phys. Math. Model. Oil Gas Energy 2 (1), 82–91. https://doi.org/ 10.21684/2411-7978-2016-2-1-82-91

[24] Uma, M. J., Yun, H., Jeong, C. S., and Heo, J. H. (2011). Factor analysis and multiple regression between topography and precipitation on Jeju Island, Korea. J. Hydrol. 410:189–203. https://doi.org/10.1016/j.jhydrol.2011.09.016

[25] Aydin, G. (2014). Production modeling in the oil and natural gas industry: An application of trend analysis. Pet. Sci. Technol 32:555–564. https://doi.org/10.1080/10916466.2013.825271