What Is a Digital Oilfield?

The central idea of the digital oilfield is to create a “digital twin”—a digitized replica, in software—based on data from sensors in the oilfield. By analyzing these data in near real time, an oil and gas company could gain valuable insights to significantly boost production, improve operational efficiency, and enhance protection of health, safety, and environment (HSE) in numerous ways.

The digital oilfield is a core component of digital transformation in the oil and gas industry, as leading companies like Royal Dutch Shell embrace 21st century information technologies to drive projected annual value measured in billions of dollars. For example, Shell is deploying artificial intelligence to predict performance degradation for more than 500,000 control valves across its operations globally—a solution that manages more than 2 million machine learning models. This use case alone is expected to drive hundreds of millions of dollars in annual value.

Other representative use cases in Shell’s digital transformation roadmap include predictive maintenance of electric submersible pumps; predictive corrosion detection; remote asset inspection; and detection and prevention of safety hazards at gas stations and stores (e.g., people smoking near gas pumps).

The digital oilfield concept has been around for more than 20 years, ever since oil and gas companies started deploying sensors in the 1990s. But the vision remained unrealized, due to three missing pieces of technology:

  1. Reliable high-speed data transmission capabilities;
  2. Cost-effective large-scale computing resources; and
  3. Analytic methods powerful enough to make use of the velocity and volume of incoming data.

In the last few years, the missing pieces have fallen into place: 4G connectivity is now ubiquitous, large facilities have fiber connections, and the coming 5G technology will even further enhance digital oilfield communications. Elastic cloud infrastructure (via private as well as public services like AWS and Azure) provides unlimited, low-cost compute resources. And a powerful new generation of artificial intelligence machine learning technology has emerged to derive insights from massive volumes of oilfield data.

 

Digital oifieldDigital oilfield capabilities enable data to be captured from both onshore and offshore oilfields and stored, processed, and analyzed in the cloud to create game-changing insights and significant outcomes for oil and gas companies.

How Can the Digital Oilfield Create Value?

Today the digital oilfield—and digital transformation of the oil and gas industry more broadly—is becoming a reality, with the potential to create enormous value. In fact, the World Economic Forum (WEF) estimates that digital transformation of oil and gas can create up to $2.5 trillion in new value globally by 2025. Oil and gas companies can capture significant value in under 12 months from four high-value digital oilfield use cases:

1. Production Optimization

Oil and gas companies can now apply sophisticated AI software to visualize, analyze, and optimize upstream production operations. All available data can be harnessed to train advanced AI machine learning models that continuously and accurately estimate hydrocarbon state across wells, pipelines, and network assets. This continuous virtual metering enables operators to back allocate production to individual wells, manage field constraints in real time, and identify well optimizations.

Learn more with the BHC3 Production Optimization application.

2. Predictive Maintenance and Reliability

Unplanned production stoppages from equipment failures and process upsets pose major risks and costs for oil and gas companies. Predictive maintenance and reliability capabilities enable companies to leverage AI-based insights to address equipment and process risks at the level of entire facilities and systems. These capabilities identify anomalies, provide prioritized alerts to operators, recommend prescriptive actions, and are key enablers of effective remote operations centers. AI analysis of historical equipment performance also enables cost reduction and increased availability by transitioning from scheduled to condition-based maintenance.

Learn more with the BHC3 Predictive Asset Maintenance application.

See video about the use of predictive maintenance for oil field equipment.

 

3. Parts and Inventory Management and Optimization

Oil and gas companies often carry excess inventory of parts and equipment in case of unplanned downtime of oilfield assets. Advanced AI techniques now make it possible to reduce inventory levels and costs, while maintaining stock when, and where, it’s needed. Unlike previous generations of inventory management applications—that were rules-based and not designed to learn from data—today’s solutions use sophisticated machine learning algorithms to continuously analyze data and optimize inventory for each part or product.

Learn more with the BHC3 Inventory Optimization application.

4. Health, Safety, and Environmental Protection

Digital oilfield technologies can be leveraged to more effectively monitor and ensure worker health, safety, and environmental protection—the most important concerns for oil and gas companies. For example, remote monitoring powered by computer vision and sensor data enables companies to more quickly and accurately detect corrosion and potential leakages. AI-enabled predictive analytics can help identify and prevent equipment failures that could harm workers and the environment.

What Are the Benefits of the Digital Oilfield?

The ability to continuously analyze comprehensive oilfield data and generate predictive insights delivers multiple benefits:

  • Improved health, safety, and environmental impact. Oil and gas companies can more effectively predict, prevent, and respond to issues such as potential leakages or catastrophic equipment failures. This translates into better protection for workers’ health, safety, and the environment.
  • Increased production, asset utilization, and revenue. Oil and gas companies operate in a volatile market environment, with downward pressure on prices and increasing production costs. Predictive maintenance and production optimization capabilities contribute to greater efficiency, yield, and revenue.
  • Decreased downtime and lost production revenue. Significant revenue is lost due to production stoppages from process upsets and equipment failures—ranging from tens of thousands to several million dollars a day from a single outage. The ability to predict and prevent equipment failure helps avoid or reduce these losses.
  • Reduced maintenance and inventory costs. Unexpected maintenance increases costs by creating the need to deploy technicians at unscheduled times and to maintain a suboptimal supply of parts in inventory. Companies can substantially reduce these costs through predictive maintenance as well as parts and inventory optimization.

How to Implement the Digital Oilfield

To successfully implement digital oilfield capabilities, oil and gas companies need to follow the proven guidelines of enterprise technology projects. Three keys to success stand out:

1. Identify high-value use cases that will return results within 6 to 12 months.

The probability of digital oilfield success increases when the focus is on well-defined, high-value use cases with positive ROI expected in 12 months or less. Oil and gas companies are encouraged to scope and tighten the focus of proposed projects to meet these goals.

All too often companies attempt to boil the ocean, launching ill-defined, multi-year projects that produce little or no results. The four use cases discussed earlier are excellent targets that can be scoped to yield measurable results within 6 to 12 months.

2. Leverage off-the-shelf SaaS solutions when possible.

Oil and gas companies have a choice whether to build or procure digital oilfield capabilities. Proven solutions for a number of well-defined use cases are commercially available. These can be acquired as AI software-as-a-service solutions, that speed time to market and reduce deployment risk.

Commercial solutions should be evaluated based on their end-to-end capabilities in meeting key enterprise requirements. These include the ability to process large volumes of disparate data, scalability, and extensibility, as well as customer references. Evaluations by independent analysts like IDC are helpful resources.

3. Take a model-driven approach when building custom solutions.

In some cases, companies will choose to internally develop digital oilfield capabilities to address specific use cases for which custom-built applications are the best solution. In order to accelerate development and reduce risk, companies are advised to take a model-driven approach that minimizes complexity and coding effort required to build the application. A model-driven approach can reduce the time, effort, and code required to build a digital oilfield solution by a factor of 40x or more.

Beyond the Digital Oilfield

While the digital oilfield focuses on upstream operations, companies can realize additional value from digitally transforming their entire value chain — upstream, midstream, and downstream. As with the digital oilfield, the core enabler is the ability to capture all the data generated throughout the value chain, create a unified data image, and apply sophisticated AI.

All of the pieces are in place now to begin realizing the full potential of the digital oilfield and beyond. For oil and gas companies, the next steps are to identify use cases, build a roadmap, deploy the right technology stack, and get going.