Total and Google Cloud have agreed to jointly develop artificial intelligence (AI) solutions applied to subsurface data analysis for oil and gas exploration and production.
The agreement focuses on the development of AI programs that will make it possible to interpret subsurface images, notably from seismic studies (using Computer Vision technology) and automate the analysis of technical documents (using Natural Language Processing technology).
Under the partnership, Total geoscientists will work side-by-side with Google Cloud’s machine learning experts within the same project team based in Google Cloud’s Advanced Solutions Lab in California.
“Total is convinced that applying artificial intelligence in the oil and gas industry is a promising avenue to be explored for optimizing our performance, particularly in subsurface data interpretation,” Marie-Noëlle Semeria, senior vice-president, Group CTO at Total, said in a statement. “This builds on the strategy being developed at Total, where AI is already used, for example, in predictive maintenance at facilities.”
Total started applying artificial intelligence to characterize oil and gas fields using machine learning algorithms in the 1990s. In 2013, Total used machine learning algorithms to implement predictive maintenance for turbines, pumps and compressors at its industrial facilities, generating savings of several hundred million dollars.
Today, Total teams are exploring multiple machine learning and deep learning applications such as production profile forecasting, automated analysis of satellite images or analysis of rock sample images.
“We believe that the combination of Total’s geoscience expertise and Google’s artificial intelligence skills will ensure the project’s success. Our ambition is to give our geoscience engineers an AI personal assistant in the next few years that will free them up to focus on high value-added tasks,” stated Kevin McLachlan, senior vice-president Exploration for Exploration & Production at Total.
“We are keen to engage our best AI engineers to work with Total’s geosciences’ experts,” added Paul-Henri Ferrand, president of Global Customer Operations Google Cloud.
Geosciences is a field that differentiates oil companies from each other, said Jean-Michel Lavergne, Total senior vice-president, Strategy, Business Development, R&D - Exploration & Production. “Geosciences allow us to find new sources of oil and gas faster and better than our competitors.”
Geoscience interpreters typically spend more than half their time gathering the data they need to be able to perform the value-added work, Lavergne said.
“The aim of this AI project is to shorten the time our teams spend on prep work so they can focus on value-added tasks. There’s a lot of work to gather documents, sort them, do the preliminary analytics: Where are the faults? Where are the channels? According to our specialists and Google’s, that work could be done by AI, allowing our interpreters to sit down at their workstations and get straight to the nuts and bolts.
“AI is designed for that: managing and sorting big data to provide a usable base. The agreement with Google is a test. We don’t know if we can teach machines to recognize faults on seismic images. We’re giving ourselves two years for proof of concept.”
Part of the project will be to conduct the complicated “recognition” work when it comes to faults on seismic images, which are all different, even if adjacent, he added.
“Google offers the best partnership format, because we want to work together to jointly develop solutions that work. And Google is the company the furthest ahead in terms of technology. The combination of the two determined our choice.”