Energizing the Oil and Gas Industry with AI

An industry built on ancient fossils is becoming a trend-setter in artificial intelligence (AI). Surprising? Maybe, but the reasons are clear. Buffeted by an unprecedented downturn that shows no signs of letting up, the Canadian oil & gas (O&G) industry is turning to innovation and technology in a bid to boost efficiency and buoy profits.

Added to that is the global spotlight on sustainable practices that reduce emissions and water consumption, prompting O&G companies to seek new ways to optimize upstream operations and eliminate practices that waste time and money.

In Alberta, the heartland of the O&G industry in Canada, industry leaders are beginning to modernize business models through a savvy combination of data analytics, AI and machine learning – and the results are nothing short of revolutionary.

Data: The new oil

From commercializing its first oil well in the late 1850s to becoming a leader in digital technology in the 1970s, Canada has always exhibited ingenuity in solving problems below the earth. The secret to staying one step ahead in a highly competitive industry? In a word, innovation.

Today, data analytics and machine learning are breathing new life into O&G. The oil industry is literally awash in data – after all, a single drilling rig generates terabytes of data daily – but until recently, only a small fraction has been used to create new business value.

As UK data science pioneer Clive Humby famously said, “Data is the new oil. It’s valuable, but if unrefined it cannot really be used… Data must be broken down and analyzed for it to have value.”

O&G is beginning to capitalize on the opportunities made possible by combining structured and unstructured data with innovative technology. The door is wide open for machine learning and AI to play a pivotal role in turning the tide back to black for Canadian O&G companies.

Predicting upsets and optimizing production with AI

Optimization of the end-to-end oil and gas value chain – where multiple plants, processes and assets are interdependent – has always been a complex challenge for upstream O&G operations. Now, a new AI solution is making it possible to get barrels out of the ground more efficiently and cost-effectively. Here’s how it unfolded.

Two years ago, one of Canada’s largest integrated oil and gas producers began working with IBM to apply the latest AI and data science methodologies to improve production optimization within their upstream operations facilities. Their goal was threefold: optimize across siloes, flag upsets early for timely response and identify actionable opportunities in real-time.

Christened “Production Optimization,” the solution uses advanced AI models and data science methodologies to optimize end-to-end production. Plant operators are placed in full control of process upset management and opportunity awareness, enabling them to predict and minimize plant upsets and act quickly on valuable opportunities in real time.

The project scope was huge – encompassing 35 individual plants, staffed by thousands of front-line operators, engineers and supervisors across 12 individual business units. Over one hundred machine learning models in a multi-layered approach were applied in a ‘systems of systems’ approach which included advanced AI models for a predictive systems layer.

Today, plant general managers are using the solution to maximize production performance and minimize energy use via a user interface that instantly delivers a comprehensive picture of their plant operational environment anytime, anywhere, on any device. The Production Optimization solution:

  • Predicts plant upsets well before they happen with a high degree of accuracy.
  • Continuously monitors production to provide recommendations that will maximize production volume, quality, inventory levels, profitability and more.
  • Rapidly generates new production schedules and creating a new plan in just a few minutes.

Making money-saving decisions every day

Production Optimization is designed to quickly pay for itself with the multi-million-dollar savings and new efficiencies generated from rapid ROI. Firsthand, this company is seeing how trustworthy data can be turned into relevant insights to make money-saving decisions.

Having a single picture of all the plants in an upstream operation has never been possible before – and for this major player in O&G, it is providing a sure path to optimization and cost savings. Now that they are capitalizing on the real-time decision making made possible by AI, there’s simply no going back.

How AI could change the future of O&G

With plenty of data accumulated over the years from conventional oil and gas production, the biggest game for AI in the upstream is interpreting, analyzing and modelling that data to enhance existing production, to extend the life of existing wells, or bring older wells back to life.

AI is poised to drive unprecedented operational productivity and efficiency in O&G. AI allows machines to interpret, act and learn from data by combining digital technologies such as machine learning, natural language processing and robotics. By augmenting human decision making through real-time insights, AI has the power to optimize and transform upstream operations.

Worldwide, the potential payoff from data-driven decision-making is enormous, including billions of savings from productivity improvements, reduced water usage and lowered emissions. Yet, according to a World Economic Forum report, only 13% of the world’s O&G companies are using data-driven insights to reduce waste and streamline operations, both upstream and downstream.

Imagine the effect widespread adoption of AI could have on productivity and operations.

For more information visit ibm.com/industries/oil-gas

Dear user, please be aware that we use cookies to help users navigate our website content and to help us understand how we can improve the user experience. If you have ideas for how we can improve our services, we’d love to hear from you. Click here to email us. By continuing to browse you agree to our use of cookies. Please see our Privacy & Cookie Usage Policy to learn more.