Recent technological advances have meant that oil and gas operators now produce plenty of data, and the amount being generated is increasing substantially each year.
‘Big data’ refers to the extremely large and complex data sets that may be analysed computationally to reveal patterns, trends, and associations. It includes unstructured (not organised and text-heavy) and multi-structured data (including different data formats resulting from people/interactions).
The three Vs are defining aspects of big data; volume (the quantity of data or information); variety (the variety of the information); and velocity (the speed in which it is collected). In recent times, two more Vs have been added to the mix; veracity (the accuracy of the data); and value (the ability to transform the large amounts of data into business).
The oil and gas industry has traditionally been poor at data management. Typically, it was only when profits dropped that the industry started to investigate how to use data to improve operational efficiency.
However, this approach is less prevalent now according to Ravindra Puranik, Oil and Gas Analyst at GlobalData.
“Many players, across the value chain, are taking an enterprise-wide view to data, and applying analytics to improve existing business processes and to develop new revenue streams,” Puranik detailed.
Aside from this, big data also has the potential to bolster occupational safety and improve environmental and energy outcomes.
However, there are still barriers to the implementation of big data, particularly given that much of an oil company’s upstream data is created on remote assets and often stored in disparate, disconnected infrastructure. Moreover, there is a scarcity of data scientists with a working knowledge of the oil and gas industry.
Despite this, Puranik expects that big data in the industry will experience incremental growth once it overcomes these hurdles, and that the growth will be further accelerated by concerns such as falling profit and future uncertainty from renewables.
According to Wood Mackenzie, embracing advanced technologies in the upstream sector could see annual cost savings of US$75 billion per annum from digitalisation by 2023, and these savings could be realised at every stage of the upstream lifecycle.
“Digitalisation offers multiple prizes in exploration,” said Greig Aitken, principal analyst in Wood Mackenzie’s corporate analysis team. “The biggest benefit would be to uncover new resources. This may be from better processing of seismic [data], or new understanding of well logs and chemical analysis.”
ADNCO, BP, Chevron, ConocoPhillips, Equinor, ExxonMobil, Gazprom, Rosneft, Repsol, Royal Dutch Shell and Woodside are among the major oil and gas players exploring big data to manage the companies’ vast amounts of data.
ExxonMobil to collect all operating data
ExxonMobil is rolling out an industry-leading project that enables the company to collect all operating data from its refineries and chemical plants – with speeds up to one billion bits per minute – into a high-performing computing environment.
The ExxonMobil Manufacturing Support Data Lake combines the company’s rich history in energy innovation with its deep expertise in advanced computing.
By applying advanced analytics to the data, ExxonMobil can ensure the company’s sites run more efficiently as well as with potentially fewer emissions.
At the company’s Permian Basin oilfield in the U.S., big data is expected to help the company add an extra 50,000 barrels of oil per day to production by 2025.
BP’s problem-solving supercomputer
In 2013, BP opened its state-of-the-art Center for High-Performance Computing (CHPC) in Houston, which houses one of the world’s largest ‘supercomputers’ for commercial research and processing enormous amounts of data.
Replacing a previous facility, the supercomputer was established primarily to help with seismic imaging, but its vast data-crunching ability is now used by the whole organisation. For example, the CHPC has provided critical support to the company’s upstream segment – enabling BP’s computer scientists and mathematicians to achieve industry breakthroughs in advanced seismic imaging and rock physics research to help with reservoir modelling.
Additionally, BP’s downstream business uses the supercomputer for fluid dynamic research to study hydrocarbon flows at refineries and pipelines to improve operational safety.
Since the CHPC opened, BP has more than quadrupled its computing power and doubled its storage capacity. As at 16 April 2020, the supercomputer had 16.3 petaflops* of computing capability, allowing it to process more than 16 million billion calculations per second and complete a problem in an hour that would take a standard laptop nine years.
“Our investment in supercomputing is another example of BP leading the way in digital technologies that deliver improved safety, reliability and efficiency across our operations and give us a clear competitive advantage,” said Ahmed Hashmi, BP’s head of upstream technology.
BP recently announced that it would be joining forces with the U.S Government, leading universities and some of the world’s largest technology companies to help researchers halt the spread of COVID-19.
BP is expected to provide access to its significant supercomputing capability and scientific expertise to the public-private consortium formed in March 2020 by the White House’s Office of Science and Technology Policy, the U.S. Department of Energy and IBM.
*A petaflop of processing speed is one thousand trillion floating-point operations, or ‘flops’, per second.
Sources: Big Data analytics in oil and gas industry: An emerging trend, Mehdi Mohammadpoor and Farshid Torabi
