At the speed of thought: cognitive technology in oil & gas

31 May 2016 (Last Updated May 31st, 2016 18:30)

Using cognitive computing technologies developed by IBM, Repsol has found new ways to match the power of machines with the decision-making qualities of their masters. Santiago Quesada, director of exploration and production technology at the Repsol Technology Centre, explains how the two companies are working together to facilitate human-computer collaboration in the oil & gas industry.

At the speed of thought: cognitive technology in oil & gas


In October 2014, Repsol launched the first global cognitive technology for the oil and gas industry in collaboration with IBM. The project aims to develop cognitive technologies to allow individual decision-makers to work with computers more efficiently than ever before. This is made possible by enhancing the industry's ability to source, analyse and filter big data in order to make it more consumable so that decision-makers can act upon the data more effectively.

In an environment of ever tighter margins, cognitive technology can help energy companies increase the productivity of their oil and gas fields and minimise exploration risk when searching for new resources. The objective of Repsol's collaboration with IBM was to leverage IBM's cognitive computing capabilities to help Repsol reduce the risk and uncertainty of oil field acquisitions and maximise the yield of existing oil fields while reducing costs.

When it comes to the optimisation of reservoir production, a cognitive environment is able to adapt to the individual needs of a varied set of technical experts, equipping them with the tools needed to analyse data from numerous sources. Moreover, technicians are also able to tie in existing production models with the analysed data and adjust them so that they more accurately match current production as time goes on.

Building on existing cutting-edge technology

The collaboration was partly inspired by Repsol's Excalibur project, a collection of mathematical techniques used to optimise Repsol's existing oil fields. The technology also enables oil fields to be quickly and accurately ranked with new investment opportunities to be identified that would be difficult to detect with traditional techniques. Excalibur was tested in remote offshore fields in Ecuador and Brazil, and has been a great source of innovation and intellectual property. During additional tests carried out in the North Sea oil field, Excalibur achieved an improvement of 9% on the best solution published to date by other companies.

"The collaboration was partly inspired by Repsol's Excalibur project, a collection of mathematical techniques."

The technology being developed by Repsol and IBM has also drawn inspiration from another collaborative project known as the Pegasus project. With this technology, Repsol has been able to improve the safety, efficiency and profitability of upstream operations by constructing more fluid conceptual and geological models, exploring hypothetical scenarios to guarantee the best decisions in the E&P of hydrocarbons.

The Pegasus project aims to strengthen the capacities of technical equipment, through a much more efficient interaction between humans and computers. The technology is capable of analysing hundreds of thousands of documents, reports and data, looking for trends and connections between them in order to propose the most appropriate hypotheses and solutions.

Improved decision-making through cognitive technology

Since October 2014, Repsol and IBM have put the cognitive technology under rigorous testing at IBM's Cognitive Environments Laboratory (CEL) in New York and Repsol's Technology Centre in Madrid. Repsol expects early results during the first half of 2016.

The enhancement of the decision-making process for the acquisition of new oil fields, both onshore and offshore, requires strategic decisions across a variety of technical experts. In addition, the purchase of new assets requires large financial investments which are sometimes based on uncertain data. However, the cognitive system can interpret data through the use of natural language processing. With the help of the Repsol and IBM collaboration, an expert is able to guide the computer system to quickly produce summaries for specific queries and run simulations that are able to inform the decision-making process and reduce uncertainty inherent in the oil and gas E&P.

Repsol and IBM plan to launch several pilots during the course of 2016 across all five continents in which Repsol operates. Both companies hope that by the end of 2017 they will have a cognitive system in place that will assist in the acquisition of new oil and gas plays.

"The technology will also introduce new real-time factors which should be considered when making decisions."

Scientists will also experiment with a combination of traditional and new interfaces which are based upon gestures, robotics and advanced visualisation and navigation techniques. By using these techniques, researchers can leverage sophisticated models of human characteristics, preferences and biases that may be present in the decision-making process. The technology will also introduce new real-time factors which should be considered when making decisions, such as current news events around economic instability, political unrest and natural disasters.

Cognitive environments have the potential to facilitate human-computer collaboration at 'the speed of thought', which can lead to a more informed and robust decision-making processes. In the case of Repsol and IBM, the innovative technology will not only improve the way oil companies visualise and map oil plays, it will also help them to make strategic decisions about the long term development of their E&P activities.

Both companies will continue to develop these cognitive technologies and hope to extend their use to other areas including downstream operations and refineries in order to help secure future energy supplies.