Watson to help find new sources of oil

World’s first cognitive-technologies collaboration for oil industry applications
October 30, 2014

IBM’s Cognitive Environments Lab researchers are developing software agents called “cogs” to help energy company Repsol make better decisions on acquiring new oil fields (credit: Jon Simon/Feature Photo Service for IBM)

Scientists at IBM and Repsol SA, Spain largest energy company, announced today (Oct. 30) the world’s first research collaboration using cognitive technologies like IBM’s Watson to jointly develop and apply new tools to make it cheaper and easier to find new oil fields.

An engineer will typically have to manually read through an enormous set of journal papers and baseline reports with models of reservoir, well, facilities, production, export, and seismic imaging data.

IBM says its cognitive technologies could help by analyzing hundreds of thousands of papers, prioritize data, and link that data to the specific decision at hand. It will introduce “new real-time factors to be considered, such as current news events around economic instability, political unrest, and natural disasters.”

Dealing with big-data complexity

The oil and gas industry boasts some of the most advanced geological, geophysical and chemical science in the world. But the challenge is to integrate critical geopolitical, economic, and other global news into decisions. And that will require a whole new approach to computing that can speed access to business insights, enhance strategic decision-making, and drive productivity, IBM says.

This goes beyond the capabilities of Watson. But scientists at IBM’s Cognitive Environments Laboratory (CEL), collaborating with Repsol, plan to develop and apply new prototype cognitive tools for real-world use cases in the oil and gas industry. They will experiment with a combination of traditional and new interfaces based upon spoken dialog, gesture, robotics and advanced visualization and navigation techniques.

The objective is build conceptual and geological models, highlight the impact of the potential risks and uncertainty, visualize trade-offs, and explore what-if scenarios to ensure the best decision is made, IBM says.

Repsol is making an initial investment of $15 million to $20 million to develop two applications targeted for next year, Repsol’s director for exploration and production technology Santiago Quesada explained to Bloomberg Business Week. “One app will be used for oil exploration and the other to help determine the most attractive oil and gas assets to buy.”


IBM | Repsol and IBM Transform the Oil Industry