Decision Support System Utilizing Hybrid Linear Regression Algorithm for Oil and Gas Production

Document Type : Research Paper

Authors

Department of Information Technology Management, Faculty of Management and Accounting Allameh Tabataba’i University, Tehran, Iran

Abstract

Intelligent Decision Support Systems (IDSS) have become increasingly essential for enhancing prediction accuracy, resource planning, and operational stability in the oil and gas sector. Traditional linear regression–based models often fail to capture nonlinear patterns inherent in petroleum operational datasets, resulting in reduced forecasting reliability. Recent research highlights the importance of hybrid approaches that integrate statistical and machine learning techniques to improve predictive performance and support upstream decision-making.This study proposes a hybrid model combining Linear Regression (LR), Random Forest (RF), and Artificial Neural Network (ANN) algorithms to enhance oil production prediction accuracy and reduce production instability. The model was evaluated using 9,208 operational records from the Azadegan oil field. Results demonstrate a 17% reduction in prediction error and a 15% decrease in production instability, confirming the superiority of hybrid predictive models for upstream decision support. These findings align with prior studies emphasizing the effectiveness of AI-driven hybrid systems in optimizing petroleum production forecasting.

Keywords

Main Subjects

References

[1]. SIRCAR, A., Yadav, K., Bist, N., & Oza, H. (2021). Application of machine learning and artificial intelligence in oil and gas industry. Petroleum Research, 6(10), 379-391. doi: https://doi.org/10.1016/j.ptlrs.2021.05.009.##
[2]. Nikitin, N. O., Revin, I., Hvatov, A., Vychuzhanin, P., & V. Kalyuzhnaya, A. (2021). Hybrid and automated machine learning approaches for oil fields development: the case study of volve field, North Sea. Computers & Geosciences, 161(3), 15. Doi:org/10.1016/j.cageo.2022.105061. ##
[3]. Wang, J., & Zhang, Y. (2025). A hybrid system with optimized decomposition on random deep learning model for crude oil futures forecasting. Expert Systems with Applications, 272, 126706. doi: org/10.1016/j.eswa.2025.126706. ##
[4]. Raad Z. Homod, G. N.-K.-S. (2023). Crude oil production prediction based on an intelligent hybrid modelling structure generated by using the clustering algorithm in big data,. Geoenergy Science and Engineering, 340, 127634. doi: org/10.1016/j.geoen.2023.211703. ##
[5]. Atesongun, A., & Gulsen, M. (2024). A hybrid forecasting structure based on arima and artificial neuralnetwork models. Applied Sciences, 14(16), 7122. doi: org/10.3390/app14167122. ##
[6]. Hanif, H. R. (2024). The role of artificial intelligence in optimizing oil exploration and production. Eurasian Journal of Chemical, Medicinal and Petroleum Research, 3(5), 176-190. doi: doi.org/EJCMPR/2024124442. ##
[7]. Al Dwood, R., Meng, Q., Ibrahim, A. W., Yahya, W. A., Alareqi, A. G., & AL-Khulaidi, G. (2024). A novel hybrid ANN-GB-LR model for predicting oil and gas production rate. Flow Measurement and Instrumentation, 100, 102690. doi: org/10.1016/j.flowmeasinst.2024.102690. ##
[8].حیاتی جعفربیگی، س.، و مرادی نافچی، ف. (1403). فرصت‌ها و چالش‌های پایش وضعیت هوشمند تجهیزات دوار در صنایع نفت و گاز. نوزدهمین کنفرانس سیستم‌های هوشمند ایران. ##https://icis2024.ir/files_site/files/r_25_241230233104.pdf.
[9].عطربرمحمدی، س.، خیرالهی، ح.، آیت الهی، س. و پیشوائی، س. (1403). به‌کارگیری مدل‌های یادگیری ماشین برای پیش‌بینی تشکیل امولسیون اسید و نفت در آزمایش‌های استاتیک اسیدکاری با استفاده از بانک اطلاعات ترکیبی. پژوهش نفت، 91-73. doi:10.22078/pr.2024.5452.3426. ##
[10]. Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative research in psychology, 3(2), 77-101. doi:10.1191/1478088706qp063oa. ##
[11]. عابدی جعفری، ح.، تسلیمی،  م. و فقیهی، ا. (1390). تحلیل مضمون و شبکه مضامین: روشی ساده برای تبیین الگوهای موجود در داده‌های کیفی. مجله اندیشه در مدیریت راهبردی، 198-151. ##doi:10.30497/smt.2011.163.
Journal of Petroleum Research
Volume 35, 1404-4 - Serial Number 143
November and December 2025
Pages 99-124

Files

Share

How to cite

Statistics