Artificial intelligence methods adapted to the CO₂-assisted oil and gas resource endowment of the Middle East

Abstract

The Middle East, as the world's most resource-rich region for oil and gas, features complex reservoir geology, a long development history, and massive production systems, facing multiple challenges such as enhancing recovery, reducing development costs, and achieving a green transition. Artificial Intelligence (AI) technologies provide revolutionary tools to address these challenges. This paper systematically reviews AI methods adapted to the specific oil and gas resource endowment of the Middle East, covering the entire industry chain including geological exploration, reservoir characterization, production optimization, equipment operation and maintenance, and energy transition. It analyzes the specific AI application requirements for scenarios prevalent in the region, such as high-temperature, high-pressure carbonate reservoirs, fractured-vuggy reservoirs, and secondary development of mature fields. Key technological pathways, including data-physics integration, multi-scale modeling, digital twins, and theory-guided machine learning, are outlined. Combined with the strategic practices of Middle Eastern National Oil Companies, the challenges and future directions for AI implementation are discussed. The research indicates that building a synergistic innovation system integrating ``domain knowledge + big data + high-performance computing" is crucial for unlocking the potential of Middle Eastern hydrocarbon resources and driving the industry's intelligent transformation.

Document Type: Invited review

Cited as: Li, C. Artificial intelligence methods adapted to the CO2-assisted oil and gas resource endowment of the Middle East. Computational Energy Science, 2025, 2(3): 111-116. https://doi.org/10.46690/compes.2025.03.04

References

Al-Hashmi, A. R., Divers, T., Al-Maamari, R. S., et al. Improving polymer flooding efficiency in Oman oil fields. Paper SPE SPE EOR Conference at Oil and Gas West Asia, Muscat, Oman, 21-23 March, 2016.

Abdullatif, O. Geomechanical properties and rock mass quality of the carbonate Rus formation, Dammam dome, Saudi Arabia. Arabian Journal for Science and Engineering, 2010, 35(2): 173-197.

Aramco and Microsoft deepen industrial AI push.

Bhattarai, K., Yousef, M. Petroleum resources and energy transitions in the MENA region: Geopolitical and economic implications, in the Middle East, edited by K. Bhattarai and M. Yousef, Springer, Cham, pp. 137-166, 2025.

Expansion roadmap of AI applications for UAE’s energy giant: Calling for trillion-level infrastructure investment and securing partnerships with top-tier enterprises. (in Chinese)

Energy system of Middle East. The International Energy Agency 2026.

Kuwait Oil Company, Microsoft opens AI innovation center.

Lim, Y. Carbon capture, utilization, and storage (CCUS), in Alternative fuels for environmentally-friendly ships: Hydrogen, ammonia, bio-fuels and e-fuels, edited by Y. Lim, Nature Switzerland, Cham, pp. 67-82, 2025.

Lian, Y., Geng, Y., Tian, T. Anomaly detection method for multivariate time series data of oil and gas stations based on digital twin and MTAD-GAN. Applied Sciences, 2023, 13(3): 1891.

National Iranian Oil Company: A key player in Iran’s economy and industry. Iranian Brands 2025.

Qatar Energy’s AI strategy 2026: Fueling global AI with LNG and securing market dominance.

Srivastava, K., Singh, T. P., Pradhan, M. R., et al. Understanding data analytics and predictive modelling in the oil and gas industry (1st ed). Boca Raton, FL, USA, CRC Press, 2023.

Sonatrach: Fiber optic sensing enables high-precision intelligent oil and gas pipeline inspection. (in Chinese)

SAP expands digital transformation partnership with Qatar’s NOC.

Tariq, Z., Aljawad, M. S., Hasan, A., et al. A systematic review of data science and machine learning applications to the oil and gas industry. Journal of Petroleum Exploration and Production Technology, 2021, 11(12): 4339-4374.

Wang, H., Guo, Z., Kong, X., et al. Application of machine learning for shale oil and gas “sweet spots” prediction. Energies, 2024, 17(9): 2191.

Xu, Z., Li, S., Li, B., et al. A review of development methods and EOR technologies for carbonate reservoirs. Petroleum Science, 2020, 17: 990-1013.

Xue, L., Liu, P., Zhang, Y., et al. Status and prospect of improved oil recovery technology of high water cut reservoirs. Water, 2023, 15(7): 1342.