If you have a case study that you would like to present, please contact:
Phone: +1 (855) 709-0098
Chairperson’s Opening Remarks
Dave Lafferty, President
Scientific Technical Services
AI, Machine Learning & Business Value – Unlocking the Value Hidden in Oil & Gas IoT Data
Machine learning makes use of certain types of artificial intelligence. However, not all artificial intelligence is machine learning. In this presentation you will hear how a combination of sophisticated artificial intelligence & machine learning can help all users quickly unlock the business value found in oil & gas IoT data – whether that data is found on the edge, in a data center or in a cloud. Additionally, you will hear the unique challenges associated with turning raw data into actionable, contextualized intelligence for all users so that better business and process decisions can be made – in real–time.
Chris MacDonald, Director of Business Analytics Business Development
What it Takes to Create Value from Machine Learning for E&P
Machine learning has been around for a few decades and the E&P industry has used various algorithms for a diverse set of problems. However, not a significant amount of industry problems have been solved effectively. The challenges lie in how we leverage machine learning.
E&P industry needs to leverage an integrated and modular approach to address industry problems. They need to bring search automation to build recommendations for actions from insights from machine learning applied to E&P Big Data. They also need to use case related drilling performance and real-time big data analytics to get insights into NPT and ILT (which will be briefly discussed).
Dr. Satyam Priyadarshy, Chief Data Scientist
Morning Break and Networking
Emerging Applications of Machine Intelligence in Oil & Gas
With recent advancements in the field of embedded computing and artificial intelligence, new applications of machine learning are emerging that enable substantial improvements in the effectiveness of existing COTS sensor technology and open the way for highly autonomous capabilities in deployed systems.
This presentation will focus on recent applications of machine learning to pipeline leak detection, remote satellite sensing and communications.
Daniel Davila, Research Engineer
Southwest Research Institute
Applications of Machine Learning and Analytics: “What is it good for?”
As the Industrial Internet of Things (IIoT) has become a major topic in the oil and gas industry, much talk has focused on “the analytics engine.”
Less has been said, however, about the fuel and the product of the engine: the data that serves as input and the application of the output. While applied analytics is certainly very powerful, it is only as good as the data being analyzed.
In this talk, Dr. Mehrzad Mahdavi will discuss what kind of data is best suited for machine learning applications and how this data can be acquired.
He explains why it is essential to have the right sensors collecting the right data to get the right output: actionable information that optimizes asset production.
He also emphasizes that the end goal of any machine learning project must be defined at the outset, before the algorithm is built, to ensure success.
Dr. Mehrzad Mahdavi, Vice President - Digital Solutions
The Hunt for Data Scientists
- Breaking down your organization into individual contributors vs the unicorn data scientist
- Understanding the types of data scientists you need
Giewee Hammond, Lead Data Scientist - Upstream
Roadmap to Constructing a Top-Down Big Data and Machine Learning System
E&P organizations are turning more attention to accumulated data to enhance operational efficiency, safety and recovery. The computing paradigm is shifting, the O&G paradigm is shifting and the rise of the machine learning paradigm requires careful attention to top-down integrated systems engineering.
A system approach will be presented to stimulate out-of the-box thinking to address the machine learning paradigm.
Mark Reynolds, Senior Solutions Architect Technical E&P Applications
Pathways for Innovation in the Digital Oilfield
An expose on our most compelling findings from a series of research studies completed for a group of top E&P companies over the past year. We will explore a wide array of actual use cases, such as water management, completion optimization, asset integrity and artificial lift systems through the lens of digital innovation.
Jeremy Sweek, Partner
Bridging the Gap Between Data and Value
Data analytics projects provide tremendous value and will grow exponentially as we digitize our operations and acquire more data. By exploring case studies on predictive maintenance for artificial lift and product performance for flow assurance, we will highlight the potential value that can be realized and the best practices that are vital to the success of data analytics efforts.
Bill Robertson , Senior Manager - Enterprise Analytics
Outcome-Driven Machine Learning
- A combination of a large product footprint, decades of knowledge, and an industrial data infrastructure has enabled the development of algorithmic products that expand the offerings of an original equipment manufacturer
- Data-driven methods have been employed on subsea systems and topside equipment
- Customer interfaces have been created to provide end-user access to the data and the analytics outcome
Gilbert Chahine, Director - Data Science & Analytics
National Oilwell Varco
Using AI to Remove the Clutter, Extract Value and Gain a Holistic View of Oil and Gas Operations Using an Asset Most Companies Already Have: Data
Utilizing predictive analytics to get ahead of failures in orders of magnitude greater than with traditional computer programming
Optimizing operations by enhancing the decision making of subject matter experts
- Understanding who is in control by applying machine learning to cyber security
Brant Swidler, Manager - Customer Success
Evaluating your Organization’s Cyber Vulnerability
- Understanding ICS cyber risks
- Overview of current global ICS cyber attacks and threats
- Emerging cyber threats to ICS and potential impacts
- How can you protect your organization?
Peter Thomas, Chief Technology Officer
5:00 pm - 6:00 pm
Dave Lafferty, President
Scientific Technical Services
Machine Learning for the "Citizen Data Scientist"
Catalina Herrera, Senior Solutions Consultant
Get more out of machine learning on big data – how to overcome the biggest challenges.
- There are good reasons for why Oil & Gas firms are using less than 1% of the data gathered – because it’s hard. Despite all the productivity improvement and cost-saving opportunities offered by machine learning, data is still the problem. It’s challenging to onboard, cleanse, integrate and enrich all the different types of data. Structured, unstructured, semi-structured, etc… attend this presentation to learn more about how you can harness this data and how to overcome some of the biggest challenges in machine learning.
Arik Pelkey, Senior Director of Product Marketing
Rage against the Machine (Learning): A top level view
Francisco Sanchez, President
Houston Energy Data Science, Inc.
Morning Break and Networking
Boost your Machine Learning Success: Understanding the Flaws and Putting a Proactive Plan in Place
In early December 2016, an oil spill in Belfield, ND that measured more than 175,000 gallons was discovered by a local landowner. It is unknown how long the pipeline may have been leaking and while the pipeline had monitors and was regularly inspected, the leak was not detected.
In late January 2017, an Iowa pipeline that crosses several mid-western states, spilled almost 50,000 gallons of diesel fuel caused by an excavator not checking on the presence of underground utilities. Monitors, sensors and rapid responses coupled with algorithms provide strong foundations for managing operations.
However, all machine learning algorithms have flaws. Statistics never promise 100 percent accuracy. So how do we detect flaws and even proactively plan for them?
Different techniques for detecting and preventing problems include early human interactions with the systems as part of troubleshooting, ensuring that the ML team understands multiple methods as well as why and when to use them, revisiting models to ensure that the factors that were true when the project started are still true, learning how to recognize false positives and negatives before the machine learns bad habits, and having enough subject matter expertise in the ML team to understand how to interconnect the logic we take for granted as cognitive beings.
Early adopters of ML started small but now the industry is impatient to tackle more impactful projects where the stakes are much higher, and performance metrics misses can have devastating results. As those in the forefront of ML, we need to ensure that projects have the best chance of success.
Michele Bennett PhD, Executive - Digital Advanced Analytics
Flexible and Hybrid Electronics - Enabling Internet of Things
- Saape Design’s efforts in implementing a flexible hybrid electronic platform which senses physical quantities and sends the data to a cloud service for data aggregation.
- Saape Designs will demonstrate its current design and capabilities for common physical measurements and possible chemical measurements
- Further integration of different types of sensors with an end to end solution to make Industrial Internet of Things possible in Upstream sector of oil and gas industry
- Different machine learning algorithms like neural networks and advanced analytics capabilities to derive meaning from the raw sensor data and provide feedback loop for remedial actions
Abhilash Iyer, Research Engineer
Smart Workforce Guidance for Smart Infrastructure and Smart Industry: Getting the Job Done in the Last Tactical Mile
In Oil and Gas and other sectors, the Industrial Internet of Things (IIOT) discussion has been dominated by the technologies and benefits of analytics or smart self-optimizing machines in industry.
Similarly, strategies for smart infrastructure and cities have focused on embedded sensors, green solutions and sustainable living. In both cases, the missing topic is the workforce – the effectiveness and safety of the human at the edge where warm hands touch cold steel to maintain and operate equipment.
Smart guidance delivered on mobile and wearable devices at the right time, enabled by machine learning and a continuous understanding of worker context, ensures the workforce maintains and operates systems and equipment to reap the benefits of the ‘smart’ in infrastructure and across industry.
Contextere will share real-world examples of the value associated with smart guidance to workforces across cities and industry.
Carl Byers, Co-Founder and Chief Strategy Officer
Operationalizing Machine Learning in Oil & Gas, Tales from the Trenches
Arundo will share real-world examples from their client base as well as the lessons learned in delivering machine learning in oil & gas.
- The “best algorithm” fallacy
- From data science to operator insight
- Platform valuation, end-to-end
- Use case selection, repeatability, and delivered value:
- ○ Topside equipment CBM (predictive modeling + fleet learning)
- ○ P&ID to tag mapping
- ○ Logistics (water management to vessel route planning)
Stuart Morstead, Chief Operating Officer
Machine Learning on Subsea Applications
- Subsea environmental introduction
- Machine learning introduction
- Machine learning (neural networks, genetic algorithms …) applications on subsea environment:
- Subsea umbilicals, risers & flowlines design
- Subsea umbilicals, risers & flowlines life extension
- Subsea layout
- What is coming next?
Victor Chaves, Founder & CEO
Lessons Learned From the Front Line: Moving AI From Research to Application
In this presentation, Eric will provide a historical perspective on the evolution of machine learning technologies and development of tools the drive the industry. From there, he’ll trace the transition of these technologies from “research” to deployed solutions, reviewing specific examples such as quick development of IIoT fault detectors to geologic material classification from well core CT and image data.
Eric Jones, CEO
Lunch sponsored by Enthought
Machine Learning Applications in Production Optimization and Operational Excellence Panel:
Sarah Tamilarasan, Vice President
Mark Allen, Chief Petroleum Engineer
Pradyumna Dhakal, Data Analyst
Pioneer Natural Resources
Christopher Robart, Managing Director
Tyler Williams, Technology Venturing Manager - Shell Technology Ventures
Accessing the Impact of Emotion AI in the Field
Our emotions have an appreciable influence on every aspect of our lives, including our work environment. Although they are central to who we are, emotions are rarely explored from a data analytics point of view, especially in the context of the enterprise.
Is it possible to draw a correlation between emotional health and safety in an E&P environment? Can emotional cues in the interviewing process help to identify the best candidates for a safety critical position? This presentation will explore these questions and explore how Emotion AI could be useful in the O&G industry.”
Boisy Pitre, Emotion AI Evangelist
Machine Learning: Disrupting a Legacy Industry
- What is the future of Machine Learning in the oil and gas industry?
- What do companies need to do today to prepare for the rapidly changing future?
Alex Hendren, Founder & Lead System Architect