Producers Turn to Big Data in Downturn

As the industry grows leaner, its data banks grow ever fatter.

With data in the terabyte and exobyte range, many petroleum companies have launched “big data” initiatives to use the vast amounts of information to increase success rates and trim costs.

Information is collected by more and more devices deployed at all stages of exploration through production and delivery.

Halliburton’s chief data scientist, Satyam Priyadarshy, is well-versed on the topic.

“When we think about big data, it’s a confusing term. The definition we use is leveraging all the data by actually taking advantage of emerging technologies and analytics to create actionable and new insights from the data,” Priyadarshy said.

“‘All the data’ means historical industry data, plus real time collections and future data from mobile devices — it’s a continuous process,” he said.

Please log in to read the full article

As the industry grows leaner, its data banks grow ever fatter.

With data in the terabyte and exobyte range, many petroleum companies have launched “big data” initiatives to use the vast amounts of information to increase success rates and trim costs.

Information is collected by more and more devices deployed at all stages of exploration through production and delivery.

Halliburton’s chief data scientist, Satyam Priyadarshy, is well-versed on the topic.

“When we think about big data, it’s a confusing term. The definition we use is leveraging all the data by actually taking advantage of emerging technologies and analytics to create actionable and new insights from the data,” Priyadarshy said.

“‘All the data’ means historical industry data, plus real time collections and future data from mobile devices — it’s a continuous process,” he said.

“The more data you add, you will get new patterns and will be looking for efficiencies,” Priyadarshy said.

The speed with which data can be collected and viewed, often in real time, can provide “actionable insight at the field level,” he said.

In addition to geologic challenges, the industry faces rising extraction costs, environmental restrictions and sometimes turbulent international politics.

Competitive Edge

In a 2013 Microsoft white paper, “Drilling for New Business Value: How innovative oil and gas companies are using big data to outmaneuver the competition,” the authors note that companies are using data from myriad sources to make more confident data-driven decisions.

“Big data technology has applications across the entire oil and gas value chain – from geology and exploration to production and operations, transport and refining, and retail,” the paper stated.

“Relying on historical drilling and production data from local sites, for example, can help scientists verify assumptions when new surveys are restricted by environmental regulations. Similarly, reviewing information, such as weather patterns and ice flows, from data marketplaces can help analysts make connections with operational processes, such as the impact of storms on rigs,” the authors of the paper wrote.

In a May 2015 Forbes article, contributor Bernard Marr said, “Production forecasting is one of the first jobs – determining the likely output of the reservoir is key to determining what resources should be spent on collecting it. When this decision is data-led, operators can have more confidence that this will be done efficiently.”

Writing in Analytics magazine, Adam Farris, senior vice president of business development for Drillinginfo, suggests the industry should do more.

“Other industries are embracing big data analytics, but the oil and gas industry is just now getting the concept. The oil and gas industry has dealt with big volume, variety and velocity, but must start thinking beyond self-made boundaries to truly capture the benefit awaiting,” Farris said.

“The oil and gas industry needs more cross-fertilization. As oil and gas companies awake to the potential of analytics, many jobs will be created for data scientists, opening a portal for new applications and ideas to enter the industry,” he said.

Rise of the Machines

Farris also predicted that smarter machines will aid in interpretation and decision-making.

“Soon we will not just capture data and view it, which still requires experienced personnel to make a large number of decisions. We will have smarter solutions, with built-in intelligence, so computers can make simple decisions, while indicating a set of potential outcomes to the user in more difficult situations, helping with faster decisions based on best practices. Ultimately, costs for these operations will be cut and production will go up,” he said.

Priyadarshy said complex algorithms allow analysis of data from multiple sources in a much shorter time. This, in turn, allows faster decision-making.

But it’s not just about saving time, he said.

“How can I improve efficiency?” he said.

“We are looking for a return on innovation — return is long-term. If I get 1 million traces, I may save five days. If I get 5 million traces, will I save fives times as much? Not really. We are looking for new insights,” he added.