The oilfield designation “exploration & production” (E&P) dates back to Spindletop. Historically, however, the strongest connection between the two very different worlds often has been the ampersand. Exploration teams invest millions of dollars to collect mega-volumes of data that characterize the subsurface. Once drilling begins, however, these data frequently sit idle, untapped by production teams despite the data’s incredible value in reservoir imaging, interpretation, modeling and characterization. Today, help is on the way.

The emerging concept of a digital twin is bridging the gap between E&P by connecting all surface and subsurface components of the exploration-to-market value chain. Integrating data from smart sensors with new types of reservoir intelligence enables full-scale operational control and collaboration between the subsurface reservoir and surface operations—a means of reduced risk, significant savings and increased recovery.

Widespread adoption of cloud technology is breaking down barriers that have traditionally kept geoscientists and engineers trapped in workflow silos and prevented the day-to-day use of subsurface models in production operations. With the cloud, digitalized information can be shared easily across the enterprise, and intelligence can be made available to all stakeholders in the workflow.

The advent and maturation of Big Data analytics— both physics-based and machine learning—complete the digital twin. With terabytes of archived data, powerful, automated analytical tools are needed to create the actionable information that drives more holistic insight into improving business value.

With the massive growth in petrotechnical data, machine learning has become an essential tool for E&P applications. Emerson uses machine-learning-based technologies to characterize the hydrocarbon potential and behavior of the subsurface from large amounts of data. This enables users to describe and explain an existing outcome, predict what will happen and provide recommendations for risk management and decision-making.

Emerson uses five key elements to link subsurface intelligence to surface operations:

1. Pursue the best science, avoiding approximations by using all available data;

2. Provide a comprehensive software solution that covers the entire workflow;

3. Deliver a platform that integrates relevant thirdparty data to help unify the workflow and minimize the duplication of data;

4. Deploy software and domain expertise as a turnkey service to ensure the highest value actionable intelligence to solve problems; and

5. Leverage an extensive line of smart sensors and devices to provide secure, reliable, real-time data and communications that drive the digital twin.

By leveraging these elements, Emerson has been able to create unique value in a variety of realworld scenarios. For example, a major international oil company sought to establish an automated and repeatable workflow to capture and propagate uncertainties across project stages. The goal was to establish a durable, evergreen modeling workflow that could be easily updated as new data arrived. Combining the cloud and modern analytics, Emerson used real production data to update the original models and reduce uncertainties automatically. The result was that the operator reduced cycle times by more than 60% and achieved a better history match and understanding of reservoir uncertainty.

By connecting predictive analytics and smart sensors in a cloud-based environment, the digital twin improves E&P operations. Applied across the oil and gas value chain, it can eliminate billions of dollars in inefficiency, accelerate operations, increase recovery, minimize capex and reduce risk. Moreover, it is finally connecting E&P for benefits far more substantial than an ampersand.

Comments