AI in Oil & Gas Industry

of one

AI in Oil & Gas Industry

Two case studies of oil & gas companies that are using AI in their field operations are from ExxonMobil and Shell. Emerging trends in the use of AI in the oil & gas industry are predicting a well's yield and maintenance needs, reducing companies' carbon footprints, and automating oil hauling receipts. The most common types of AI used in the oil & gas industry are machine learning and data science, but there are applications for exploration, chatbots, and safety as well.

Case Studies of Oil & Gas Companies Using AI in Field Operations


  • ExxonMobil teamed up with IBM to use AI to "modernize all ExxonMobil’s data estates into one easy to access repository" in an effort to turn a "grueling, year-long process of churning through 2D seismic maps, tectonic and historical data into a six-month play that would detail the potential payoff of new hydrocarbon fields."
  • When ExxonMobil invested in Guyana for offshore oil exploration, the company implemented its new AI-enabled data platform that would accelerate project development and decrease the time necessary for a return on investment.
  • The AI-enabled platform allowed experts to access data from the multicloud environment, which gave them the opportunity to make faster decisions. As the project leader, Xiaojun Huang, stated, "any team member can collect data from any application from any source and make it available seamlessly through APIs."
  • Benefits gained from this AI project included a shortened planning cycle of seven months instead of nine for new well design and a 40% savings on data preparation time due to the "agile processes developed along with IBM."


  • Shell is using AI and machine learning in for precision drilling and recently adopted reinforcement learning, which helps control Shell's drilling equipment.
  • Reinforcement learning employs a reward system, which is "dependent on the outcome of the AI's 'choices'."
  • According to Daniel Jeavons, Shell's general manager for data science, with reinforcement learning "the key thing is you’re giving the [AI] agent the autonomy to make the decision. But you’re providing input into the model, so you’re providing reward or penalty functions on the basis of what’s happening in the model, and how the model responds to the set of conditions that you give it."
  • Algorithms are trained on "historical data from Shell's drilling records" and from simulated exploration and are then used to "guide the drills as they move through a subsurface."
  • The benefit gained from this AI implementation is that the human drill operator can better understand the operating environment, which leads to "faster results and less wear, tear and damage to machinery."
  • Jeavons does not expect this process to completely replace human operators, but it will allow a single human operator to support additional wells.

Trends on the Future use of AI in the Oil & Gas Industry

Predicting a Well's Yield and Maintenance Needs

  • One upcoming trend on the use of AI in the oil & gas industry is to develop neural networks to help oil and gas companies understand how a "well's yield will change over time."
  • Using numerous data points over a long enough period can tell oil and gas employees how a well will behave based on how other wells have historically performed.
  • This can so far only be used on wells that have a "sufficiently long production forecast" because the more historical data that is available, the more accurate predictions can be.
  • According to Rystad Energy's senior analyst on shale Alexandre Ramos-Peon, with enough data, the computer will "train itself somehow to guess the best value so the accuracy is as high as possible."
  • This can also help companies predict well down time for maintenance. Noble Energy is one oil and gas company that is using well yield prediction to predict and prevent well downtime based on how other wells have behaved in the past.
  • Predicting a well's yield and resulting maintenance issues is an upcoming trend because it is mentioned in several industry publications about the future of AI in the oil & gas industry.

Reducing Their Carbon Footprint

  • As "reducing carbon footprint and eliminating environmental damage is a significant concern" for oil and gas companies, it is expected that using AI to reduce their carbon footprint is an upcoming trend.
  • For example, AI can be used to find trouble spots in oil pipelines, which can "lower the carbon footprint of fossil fuels moving through them."
  • Additionally, AI can modify how a downhole pump works to reduce the crude's viscosity, which also reduces its carbon footprint.
  • This is a trend because according to experts like Matt Toohey, senior advisor of sustainability with TransAlta Corporation, "In the utility sector, which is responsible for about one-third of global GHGs, better management of data, with the use of AI and other approaches, has become essential."
  • A company that is at the forefront of this trend is BP, which has recently invested in "Chinese AI energy management tech specialist R&B."

Oil Hauling Receipts

  • The traditional system of handwriting oil hauling receipts and manually entering them into a spreadsheet has led to many inefficiencies in the oil transportation segment of the oil & gas industry.
  • Manual entry requires double checking to avoid errors and even then "data entry mistakes are rife and can cause significant disruption" to oil and gas operations.
  • Experts predict that the development of an AI system that will link oil and gas field workers to office workers will allow oil and gas companies to get a "complete and accurate view of production."
  • According to early studies, by using AI to digitally capture oil hauling run tickets (receipts), it is possible to be 99% accurate in interpreting handwritten receipts with mobile field data capture software.
  • Additionally, the data captured is of higher quality, which translates into better accounting and increased speed.
  • This is a trend because several industry publications have mentioned it in articles about the future of AI and numerous companies are working on software to solve these issues.
  • Two companies in the oil & gas industry that are using AI software to automate run tickets are Three Star Trucking and Rick's Oilfield Hauling.

Most Common Types of AI Used in the Oil & Gas Industry

Machine Learning and Data Science

  • According to Gartner, among the most common use cases for AI in the oil & gas industry are "pattern recognition, natural language processing, and image analysis and recognition."
  • Offshore Technology indicates that the two primary applications of AI in the offshore oil and gas segment are machine learning and data science.
  • Machine learning in the oil & gas industry can be used to run simulations using predictive data models and to monitor complex internal operations to allow companies to respond to potential problems before a human operator could have ever detected them.
  • Data science allows companies to make complicated data sets more accessible, which in turn "allows companies to discover new exploration opportunities or make more use out of existing infrastructures."


  • AI for exploration is already being used by ExxonMobil and it is expected this use will be popular among other oil and gas companies as well.
  • AI allows oil and gas companies to "sift precisely through signals and noise in seismic data" and create accurate geological models that helps human operators know exactly what is below a surface before they begin to drill.
  • The Dutch Central Graben in the North Sea is using AI so that engineers can "auto-track a Jurassic seismic horizon," which is generating algorithms to provide the most accurate and detailed models ever constructed. This will give oil and gas companies a better idea of where they should explore in these waters.


  • Chatbots are an AI application that oil and gas companies are already using outside of field operations. For example, Shell has two AI-based assistants called Emma and Ethan who are designed to respond to "customers' issues on common lubricant-related questions within seconds."
  • China Petroleum and Sinopec are other oil and gas companies using AI chatbots.
  • Additionally, "many of the largest Oil & Gas equipment companies in Europe have integrated chatbots to answer basic customer inquiries."


  • AI is being used by oil and gas companies to increase safety in a dangerous profession.
  • For instance, AI used for precision drilling "aims to reduce the risks that come with exploration drilling."
  • Some oil and gas companies are also using AI software that "analyzes production and sensor data (including pump pressures, flow rates, and temperatures) to predict what equipment and parts are at high risk for failures," and knowing this information helps make sites safer for human operators.
  • Moreover, AI allows companies to make more informed and faster decisions for drilling and blasting, which in turn improves both productivity and safety.