MIT-WPU Researchers Develop AI Models to Boost Oil Recovery Amid Global Energy Volatility
25 March 2026, Pune: As global oil markets face volatility driven by geopolitical tensions and supply chain disruptions, 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 and forecasting production in mature oil fields.
With oil and gas contributing nearly 32–37% of India’s total energy consumption and crude imports costing an estimated USD 161 billion, enhancing domestic production has become a strategic priority. The MIT-WPU research team is leveraging AI to address key challenges in reservoir management and reduce dependence on imports.
A team led by Dr. Rajib Kumar Sinharay, along with Dr. Hrishikesh K. Chavan, has developed a machine learning model that identifies the most suitable Enhanced Oil Recovery (EOR) techniques for complex reservoirs, achieving 91% accuracy. The model significantly cuts evaluation time from months to just hours and has been published in Petroleum Science and Technology.
In another study, Prof. Samarth Patwardhan and Dr. Soumitra Nande developed a deep learning model capable of identifying carbonate reservoir rocks with 97% accuracy—relevant to formations such as those in Mumbai High. Their work appeared in the Arabian Journal for Science and Engineering (2025).
The researchers have also created a production forecasting model with 92% accuracy (R² score), tested on real data from an Indian onshore field and published in Physics of Fluids. Additionally, an AI-based model for optimizing oil production tubing design has been patented and published under Springer Nature.
Also Read: India Issues Draft Rules for Amendment to Its Insecticides Rules, 1971
Global Agriculture is an independent international media platform covering agri-business, policy, technology, and sustainability. For editorial collaborations, thought leadership, and strategic communications, write to pr@global-agriculture.com
