Shell Drills Deep With Big Data
Increasingly, Shell uses big data to improve its operations and to increase oil and gas output of their wells. Since a couple of years they have started lowering optical fiber cables within their wells. These cables are supplied with sensors that measure everything within the wells. With this data, Shell can improve analysis of how the wells are doing and how much oil or gas is still left. What Shell exactly does with the data and how they interpret it is a secret that Chief Technologist Gerard Schotman does not want to share.
However, what is known is that these super-sensitive sensors within the optical fiber cables help Shell find additional oil in wells that were thought to have run dry. These sensors, that were created by HP, generate massive amounts of data that that is stored at a private isolated section of the Amazon Web Services. Since they started they have already collected 46 petabytes of data and the first test they did in one oil well resulted in 1 petabyte of information. Knowing that they want to deploy those sensors to approximately 10.000 oil wells, we are talking about 10 Exabyte’s of data, or 10 days of all data being created on the internet. Because of these huge datasets, Shell started piloting with Hadoop in the Amazon Virtual Private Cloud.
All the data is of course impossible to understand correctly if not properly visualized. Therefore, in order to make the data relevant information Shell is working together with IBM and DreamWorks Hollywood. An unexpected combination, but one definitely needed to visualize so much data. All data that is received from the seismic sensors are analysed by the artificial intelligence developed by Shell and rendered in 3D and 4D maps of the oil reservoirs. Although the analyses are done in the cloud, the visualizations are immediately available to the crew working at the local factory.
At the moment Shell has about 70 people working full-time in the data analysis department at the company, plus hundreds more scattered over the world who participate on an ad hoc basis. The department consists of a mix of specialists in IT, oil and gas technology, mathematicians and physicists. They are all working towards the same goal of getting more oil and gas out of the same, or new, wells.
Although Shell refuses to tell how exactly it uses what data, they are doing something remarkable with the data that they do want to share. It is a rare combination of two organisations so far apart: Shell and a few environmental organisations share data. As Gerald Schotman explains “during a brainstorm with environmental organisations we noticed that we can help migratory birds across the Sahara in their search for water. Or we share data with organisations concerning the migration of whales.”
It is definitely not a surprise that Shell makes a big effort of big data. They have a lot to win. If they manage to extract 1 percentage-point of extra oil from the wells due to big data, and all oil companies worldwide do this, it would mean additional oil for the entire world for another three years. So, Shell is quite right that they drill deep with big data!