You are Home   »   News   »   View Article

Repsol and IBM – 'cognitive' computing in E+P

Friday, March 13, 2015

Spanish oil major Repsol is working together with IBM to build a $15m-$20m system to answer difficult questions about which licenses to bid for an how to optimise production, using experts together with big data. By Santiago Quesada, Repsol's director for exploration and production technology

Oil companies continue to make high-stake decisions in the face of increasing uncertainty and geological risk based on extremely complex data sets.

Cognitive computing systems can help in exploration and production by helping individuals to better interpret big data and then make informed decisions based on that data.

As a result, companies can maximise access to better exploration areas, increase the productivity of maturing oil fields and their value, enhance safety and mitigate environmental risks.

Until recently, geoscientists have been tasked with mostly manually reading and extracting information from enormous amounts of data including journal papers reports, seismic data and models of reservoirs, wells and facilities.

Recognising the need for an intelligent solution, Repsol and IBM, leveraging years of existing collaboration, recently teamed up to develop cognitive technologies that can analyse subsurface data in order to drive improvements in exploration and production.

Based at IBM's pioneering Cognitive Environments Laboratory (CEL), the researchers will work on two prototype applications which are specifically designed to increase Repsol's strategic decision-making in the optimisation of oil reservoir production and in the acquisition of new exploration areas and production fields, both onshore and offshore.

Repsol is making an initial investment of $15 million to $20 million to develop two applications with early results targeted for late 2015.

The team will work together in New York and Madrid, with each company committing six to 10 employees to develop the technology.

People, devices and spaces

To best achieve this, the cognitive computing technology infrastructure has been designed to specifically interact with people across various devices and physical spaces.

For example, the technology is able to process questions asked by humans in natural language and sifts through information to respond with the most likely answers.

This, in turn, will enable individuals and teams to make better decisions by overcoming cognitive limitations posed by big data.

Scientists in the CEL will also experiment with a combination of traditional and new interfaces which are based upon gesture, robotics and advanced visualisation and navigation techniques.

Through these modalities, 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 such as current news events around economic instability, political unrest and natural disasters.

These tools are not intended to replace the key stakeholders such as geologists, geophysicists, engineers, investment managers, risk analysts and corporate strategists, but to assist them with building more fluid conceptual and geological models, highlighting the impact of the potential risks and uncertainty, visualising trade-offs and exploring what-if scenarios.

The new applications developed by Repsol and IBM will improve the way oil companies visualise and develop exploration and production activities.

It is envisioned that companies from other sectors will set up their own CELs to make better informed decisions and, ultimately, increase their companies' bottom lines.



Associated Companies
» IBM

CREATE A FREE MEMBERSHIP

To attend our free events, receive our newsletter, and receive the free colour Digital Energy Journal.

DIGITAL ENERGY JOURNAL

Latest Edition May-Jul 2024
Jun 2024

Download latest and back issues

COMPANIES SUPPORTING ONE OR MORE DIGITAL ENERGY JOURNAL EVENTS INCLUDE

Learn more about supporting Digital Energy Journal