Course Overview

The impact of digitization has profoundly affected the energy industry including oil and gas (digital oilfield) supply chains and utilities (smart grids). More data is available from field and process instrumentation and control systems for detailed analysis to improve decision making at all levels, from the field to the board room. The Digital Oilfield is a reality. Lower commodity prices have added the need to improve efficiency of operations, to the existing drivers of a safe and environmentally benign operations footprint, effective recovery of reserves and an attractive return on investment for shareholders. This course will take a detailed look at the opportunities, challenges and specific requirements for petroleum data analytics for the energy industry.

The Industrial Internet of Things (or IIoT) has been hyped as a major disrupter of the status quo and transformational in its impact on the business because of its ability to connect things and people in ways that hadn't been done before, provide unique services and enabling capabilities not previously possible, or certainly not as cost-effective. While this may be true in other industries, especially those with a retail consumer component, oil and gas is taking a more measured approach given lower oil prices, lower investment overall and our reputation for a conservative approach to the uptake of technologies. The industry usually wants to see proof of a good business case before overcoming a general resistance to changes.

IIoT represent the next stage of the Intelligent Oilfield which some call Digital Oilfield 2.0. The original Digital Oilfield, also known by other names including Smart Fields, Field of the Future and Integrated Operations, began around the year 2000 was IT-led and technology focused, and resulted in the expansion of automation, the use of digital devices, the addition of remote operation centers, standardization of selected workflows, and the practice of Management by Exception to operate fields. Most of Digital Oilfield activity was focused on offshore production, especially deep-water, due to the value of the assets involved.

But over time it has spread onshore, to drilling, completions and beyond. Its success onshore was initially limited to larger conventional fields, as the cost of automation for both smaller green fields and legacy brownfields was considered prohibitive. Another shortcoming of Digital Oilfield was that while it generated much more data from sensors and automation, most of the data wasn't being used to improve field operations.

The advances in data storage, computing technology and programming languages have enabled machine learning and advanced statistics, whose mathematics have long been known, to be applied to large data sets with speed and relative ease such that data analysis and interpretation can take place in near real-time, leading to applications that can directly support field operations.

Course Objectives

The emergence of large data collections and connected infrastructures (Big Data) in the energy industry has driven opportunity for operational and workflow analysis in the new digital oilfield. Being data-driven is not new to the energy industry, but past experience has shown that extracting value from large, diverse information stores can often be difficult due to the intrinsic nature of data types and unique oilfield practices. These barriers limit the ability to intelligently discover, mine, process and analyze the available information in order to add value to the organization.

A number of operating companies are establishing centers of analytics to grow new capabilities, in addition to hiring data scientists to work with existing analysts. Data Science is the hot new field with expected demand far exceeding current supply. Tech vendors and oilfield service companies are developing and offering new analytics tools and platforms for these new teams to go beyond traditional business intelligence reporting and physics-based simulations (i.e. Darcy's Law for computational fluid dynamics used in reservoir simulations) and optimization routines. There is also the ambition to make better analysts of almost every employee with "self-service BI" tools.

This course is designed to provide participants with the knowledge and skills to:

• Understand and contribute toward the significant technical challenges created by large data environments, including architecture, security, integrity, management, scalability, artificial intelligence topics, and distribution;
• Understand the principles and application of informatics, and the goals of enterprise intelligence as applied to the energy industry;
• Utilize technical/engineering skills coupled with analytics capabilities to provide enterprise-centric solutions to engineering, earth science and operations stakeholders.

Course Topics

Segment 1: Introduction to the Digital Oilfield 2.0

• A review of the objectives and results from the digital oilfield since 2000 and a discussion of what is new today (lower for much longer oil prices and emerging digital technologies)
• Convergence of OT (operational technology) and IT (information technology) systems. From sensors and control systems (SCADA), to remote decision support environments, to workflow automation, to process optimization
• The Industrial Internet of Things and Big Data Analytics for oil and gas, The search for the digital core and the five stages of digitization in oil and gas

Segment 2: Review of data analytics techniques, data management infrastructure, programming and technologies, artificial intelligence and machine learning

• Understanding of the data foundation for typical oil and gas exploration and production functions, data federation, data integration challenges, data modeling
• Review of often used analytical techniques (regression analysis, neural networks, machine learning, deep learning)
• Review of Business Intelligence (reporting), Data Visualization (dashboards, data story telling) and Artificial Intelligence approaches, the strengths and weaknesses of each.

Segment 3: Application of petroleum data analytics to upstream oil and gas used cases

• Information Intensity in Oil & Gas / Beyond Surveillance and Monitoring/ Digital Twin. Review of a practical use cases for oil and gas (predictive analytics for critical equipment, use of analytics to drill complex wellbores, optimization of completion techniques for unconventional reservoirs
• Application of cyber security issues to the digital oilfield
• System Challenges and Barriers to Adoption, what oil and gas can learn from other industries