Pune: Amid ongoing volatility in global energy markets, MIT WPU AI oil recovery research is emerging as a significant development in the oil and gas sector.
Researchers at MIT World Peace University (MIT-WPU), Pune, have developed advanced artificial intelligence (AI) and machine learning (ML) models aimed at improving oil recovery from mature reservoirs and enhancing the accuracy of production forecasting.
The MIT WPU AI oil recovery research comes at a critical time when geopolitical tensions and disruptions in global oil supply chains continue to influence energy markets.
With India’s growing economy driving increased energy demand, the need to enhance domestic oil production has become a strategic priority.
Also Read: Mahindra Research Valley to Invest ₹196 Crore in Advanced R&D Expansion
According to government data, oil and gas contribute approximately 32–37% of India’s total energy consumption, with crude oil imports costing an estimated USD 161 billion.
In this context, the MIT WPU AI oil recovery research is focused on enabling more efficient extraction from existing oil fields, thereby reducing reliance on imports.
The research is being conducted by the Department of Petroleum Engineering at MIT-WPU, the only dedicated upstream oil and gas academic department in Maharashtra.
As part of the MIT WPU AI oil recovery research, a team led by Dr. Rajib Kumar Sinharay, Professor in the Department, along with his PhD student Dr. Hrishikesh K. Chavan, has developed a machine learning model that identifies the most suitable Enhanced Oil Recovery (EOR) techniques for complex reservoirs.
The model, trained on global oil field data, achieved an accuracy of 91% in predicting optimal recovery methods. Findings from this phase of the research were published in the international journal Petroleum Science and Technology.
Notably, the AI-based model reduces evaluation time for oil recovery strategies from several months to just a few hours.
Dr. Rajib Kumar Sinharay said, “Artificial intelligence has the potential to transform reservoir management in the oil and gas industry. Our research focuses on developing data-driven tools that can help operators select the most effective recovery techniques and make more accurate production forecasts, particularly for mature oil fields.”
In another development, Prof. Samarth Patwardhan and his PhD student Dr. Soumitra Nande developed a deep learning model capable of identifying carbonate reservoir rocks with 97% accuracy.
These formations are comparable to those found in Bombay High, India’s largest offshore oil field. Their research was published in the Arabian Journal for Science and Engineering in 2025.
Further expanding the scope of the research, the team has developed a machine learning model for forecasting oil production in mature fields.
The model achieved 92% accuracy (R² score) using real field data from an Indian onshore reservoir. The findings were published in the journal Physics of Fluids, highlighting the importance of accurate forecasting in investment planning and reservoir management.
Additionally, the MIT WPU AI oil recovery research includes the development of an AI-based model to optimize oil production tubing design. This innovation helps determine the appropriate pipe size for efficient extraction.
Also Read: Suniti Solomon Research Laboratory to Drive Infectious Diseases Research at JNCASR
MIT WPU AI Oil Recovery Research Published in Springer Nature’s Algorithms for Intelligent Systems
The research was presented at the International Conference on Computational Science and Applications and later published in Springer Nature’s Algorithms for Intelligent Systems series. The team has also secured a patent for this technology.
Currently, researchers are working on identifying “sweet spots” in unconventional hydrocarbon reservoirs and developing sustainable drilling fluids suitable for high-temperature and high-pressure environments.
