Artificial intelligence (AI), which tech giant Microsoft Corp. defines as “any technique that enables computers to mimic human intelligence,” falls squarely within the digital transformation.

Exploration and production (E&P) and oilfield service (OFS) companies have been embracing digitalization for years, and the momentum is not expected to subside anytime soon. 

In a recent study, global technology market research firm ABI Research predicted that natural gas and oil companies would spend $15.6 billion on “digital transformation technologies” by 2030.

“The role of technology is evolving from helping oil and gas firms monitor their large, complex and dangerous operations, to helping them optimize their facilities to handle the volatility in their operating environments,” said ABI’s Michael Larner, industrial and manufacturing principal analyst.

Larner ticked off for NGI a list of ways in which E&P and OFS companies use AI. 

“To keep workers and staff safe, avoid leaks, and increase yields, oil and gas firms invest in technologies to analyze and monitor their operations, such as their wellheads or drills, deploy sensors to report on the condition of pipes and pipelines, and operations centers to keep themselves appraised,” said Larner.

Larner added that firms use AI to monitor local geology to understand the extent of reserves and operators to monitor local seismic activity. For instance, BP plc and ExxonMobil have demonstrated their prowess in that regard. Also applying AI is Canada-based Meg Energy Corp., which is using the technology to optimize production at its Christina Lake Facility.

“Operators also need to proactively monitor local conditions underground and another aspect requiring continuous monitoring is the weather so they can shut down facilities and evacuate staff,” Larner said.

Digital information technology firm SoftServe’s Ted Wilson, head of energy business development, told NGI that E&Ps are also using AI to optimize production, automate control systems, support worker safety, and monitor emissions and the supply chain carbon footprint.

[Special Edition: Download “ESG Reshapes the Natural Gas Pricing & Investment Landscape” now, and access NGI’s extensive coverage of where the market is headed in 2022 and beyond.]

When asked where he sees the greatest need for AI deployment in E&P and OFS operations, Larner said one area is using data analytics to gauge risks and run scenario plans for wellhead condition monitoring.

“Historically operators would move on to another location once the productivity of a site started to depreciate,” he said. “As new sources are often located in challenging environments, such as far deeper under the sea, operators are investing in analytics to model their active reservoirs to understand how they can increase yield levels.”

In the pipeline industry, “operators with assets in faraway locations are looking to digital technologies to perform remote monitoring,” Larner added.

AI offers oil and gas firms additional possibilities besides automating and improving worker safety and reducing operating expenses, noted Wilson.

He said “there is a larger opportunity in the market for AI, which is for companies to understand where an AI-based system can actually augment intelligence and create areas of optimization where humans just can’t perform as well, or as fast.”

For example, Wilson noted that machine learning (ML)-based systems help geologists and geophysicists interpret massive volumes of seismic data. Additionally, he said that ML technology could help an E&P increase well output by training itself to optimize output parameters based on variables such as equipment, production, and temperature data.

What About Human Factors?

Behaving in a more human-like manner is an ongoing quest of an AI sub-discipline called cognitive AI.

Software firm Beyond Limits’ Mike Krause told NGI that cognitive AI entails making diagnoses or predictions with AI that are based on accumulated institutional knowledge.

Krause, the company’s AI solutions senior manager, said cognitive AI adds “explainability to AI outcomes in a way that’s meaningful to people.” He added the sub-specialty refers to “the inclusion of knowledge in an AI framework.”

At a relatively basic level, an example of cognitive AI would be using an image recognition algorithm to enable AI to identify a stop sign, said Krause. An example of cognitive AI in the oil and gas industry would be encoding technology to recognize a well, he added.

“I assign attributes to it like casing, perforation…all the hardware in a well,” and then various other “explainability layers” of information, he said. “Once you layer on the cognitive view, you really expand the possibilities.”

Krause underscored the importance of granular details, particularly in an industrial AI application that is recommending, for instance, how to change a factory workflow or how to drill a multimillion-dollar well.

“I want to know why, and I want to make sure that that recommendation is built on something real and that makes sense,” he said.

Cognitive AI relies more on knowledge than data,  but Krause said it still depends on capturing “that information, or that knowledge, in the first place into a system that can then be leveraged by a broad set of users across the organization.”

Although deploying AI can help to streamline an E&P or OFS firm’s operations, it also presents legal as well as ethical issues, intellectual property (IP) attorney Terrell Miller, partner with the law firm Foley & Lardner, told NGI.

“For example, loss of jobs and workforce morale are two ethical issues that can arise when AI is deployed in a manner that may replace human employees,” he said.

Wilson, however, said that the “human element” often is a key ingredient for AI deployments to succeed.

“For example, many of our best ML solutions have required deep subject matter expertise from well engineers, operations professionals, and geoscientists in order to be successful,” he said. “Data on its own is sometime powerless without being paired with the domain knowledge from the human experts who know the patterns behind it.”

The reliance on data, in turn, can create other issues, said Miller. 

From a legal perspective, the “largely data-driven” nature of AI systems carries potential issues tied to cybersecurity and data reliability, he said.

Because many AI systems are subject to IP protections, their use “in the oil and gas industry comes with very real concerns of third-party intellectual property infringement, such as patent infringement,” said Miller. “As such, it’s important to clear any use of AI systems against existing registered intellectual property or third parties.”

Otherwise, “businesses open themselves up to a greater risk of patent, or other IP litigation, which can come with significant liability exposure,” he said.