Monday, November 9, 2020
8:00 AM - 8:40 AM
How to amplify the value of Artificial Intelligence through industry collaboration
David Crawley - University of Houston
Konrad Konarski - AI Innovation Consortium
Guillermo Romero - Vallourec
Mukesh Sahdev - Shell Trading US, Houston
Shashank Tomar - Tex-isle Supply Inc
9:00 AM - 9:40 AM
Keynote Panel – Machine Learning in Oil and Gas: Business Case, Best Uses and Future Uses
  • What are the main challenges and opportunities for machine learning implementation in the oil and gas sector?
  • To what extent has the business case for the benefits of machine learning already been accepted? Do decision makers still need to be convinced? How can the benefits be best communicated in a language everyone can understand?
  • How has the oil and gas industry adapted to new demands regarding data and machine learning in terms of talent acquisition and staff training?
  • Turning talk into action – implementation strategies, internal buy in and getting machine learning projects off the ground
  • What potential machine learning applications have most exciting potential? Where could machine learning having the most impact in the oil and gas sector moving forwards?
Dr. Kenneth Bhalla - Stress Engineering Services, Inc.
Philippe Flichy - Energy Embassy
Dr. Vikram Jayaram - Pioneer Natural Resources
Peter Lemke - BP
10:00 AM - 10:40 AM
Why Energy is Investing in Machine Learning
  • What is machine learning?
  • How can new technologies and investments be evaluated?
  • USE CASE: how is machine learning being applied at Shell?
  • Where are the opportunities for future applications of machine learning in the oil and gas sector?
Andrea Course - Shell Ventures
11:00 AM - 11:40 AM
Innovations in Emerging Energy Technology – an Outside Perspective
Anna Jarman - Walmart Technology
12:00 PM - 12:40 PM
AI Powered Enterprise Digitation – A journey of R&D and product deployment
Shuxing Cheng - Chevron
1:00 PM - 1:40 PM
Artificial Intelligence Fault Interpretation using 3D Seismic – global case studies
Lucy Plant - Geoteric
2:00 PM - 2:40 PM
Optimizing prediction of reservoir properties with artificial intelligence, big data, and the Subsurface Trend Analysis method
Kelly Rose - National Energy Technology Laboratory’
Anuj Suhag - National Energy Technology Laboratory
3:00 PM - 3:40 PM
Panel – Data, Analytics and Machine Learning
  • Machine learning and the IoT data deluge – how can machine learning models help operators gain ROI from their data?
  • Quality over quantity – the importance of analyzing the right data in a timely manner
  • The importance of cross silo, enterprise wide data strategies for machine learning programs and data analytics
  • Predictive analytics - how can machine learning-based data analytics be used with legacy data lakes to help improve future operations and prevent repeat failures?
  • What are the barriers to widespread “live” data analytics using machine learning?
  • Data security concerns and considerations
Jeremy Eade - BP
Philippe Flichy - Energy Embassy
Manoj Iragavarapu - V-Soft Consulting
Sastry Malladi - FogHorn
Afshean Talasaz - Laredo Petroleum
4:00 PM - 4:40 PM
Analytics, Machine Learning and AI for Wolfberry and WolfBone Unconventional Resources and Water Balance Assessment
Bill Fairhurst - Riverford Exploration, LLC
5:00 PM - 5:40 PM
Keynote Presentation: Practical and value-additive Machine Learning and AI for Oil and Gas
  • What does AI look like for Oil and Gas? Robots? Simulation of engineering and G&G intelligence?
  • The need for Augmenting AI solutions for practical problem solving.
  • Real workflows with examples that bring AI solutions for Oil and Gas. 
David Castineira - QRI
Tuesday, November 10, 2020
8:30 AM - 8:55 AM
Artificial Intelligence Fault Interpretation using 3D Seismic – global case studies
Lucy Plant - Geoteric
9:00 AM - 9:40 AM
Investing in Machine Learning
  • What investment strategies are there for operators interested in machine learning technology and solutions?
  • What are the advantages and disadvantages of in-house development vs joint ventures vs outsourcing?
  • What criteria can help oil and gas operators evaluate and select technology partners for machine learning projects?
  • How well are the unique challenges of the oil and gas sector recognized by cross sector machine learning solution providers?
Amy Henry - Eunike Ventures
Giancarlo Savini - Shell Ventures
10:00 AM - 10:40 AM
Leasing Behaviour Characterization via Graph Theory and Network Analysis
  • How can graph databases and network analytic be used to classify leasing entities?
  • What can be learnt about high-grade prolific investment opportunities from temporal and spatial patterns?
Chris Buie - Warwick Group
Conrad Hess - Warwick Group
11:00 AM - 11:40 AM
Panel: The Road to Automation or Augmenting Humans to Work More Efficiently?
  • Is greater automation a realistic goal for oil and gas operations? What role could machine learning play in automation?
  • What criteria are there for evaluating which processes would benefit from automation?
  • How can machine learning be used in tandem with human input to improve efficiencies and accelerate decision making?
  • How far away is the technology from providing fully automated reservoir management?
  • What potential is there for fully automated robots and drones coupled with computer vision being used for maintenance surveys?
  • What are the main barriers to greater automation of processes and operations?
Chris Humphreys - The Anfield Group
David Lafferty - Scientific Technical Services
Anuj Suhag - National Energy Technology Laboratory
12:00 PM - 12:40 PM
Unsupervized and Physics-Informed Machine Learning Analyses for Characterization of Energy Production from Unconventional Reservoirs
  • How can approaches based machine learning be used to better understand the subsurface processes, enhance oil production and minimize environmental effects?
Velimir V Vesselinov - Los Alamos National Laboratory
1:00 PM - 1:40 PM
PANEL: Aging Machinery and Volatile Pricing – The Importance of Predictive Maintenance and a Proactive Approach to Maintenance in Maximizing Lifetime of the System and Components
  • Culture shift: changing the industry attitude from reactive to proactive 
  • Where is predictive maintenance having the most impact in the oil and gas sector?
  • How can personnel safety be improved through predictive maintenance?
  • Reducing costs and streamlining project efficiency – where does the ROI and cost savings of predictive maintenance programmes come from?
  • What are the costs involved with deploying a successful predictive maintenance strategy? What are the common pitfalls to avoid?
  • What potential uses are there for a predictive approach to reliability and maintenance in the future?
David Lafferty - Scientific Technical Services
Varadarajan Nadathur - Shell
Dr. Kenneth Bhalla - Stress Engineering Services, Inc.
2:00 PM - 2:40 PM
Developing Systems and Capabilities for Aligning Operations with Predictive Maintenance Programs
  • How can systems be designed to synergise predictive maintenance resources with the strengths and experiences of maintenance engineers and asset managers?
Julian Zec - Maersk Drilling
3:00 PM - 3:40 PM
The Subsea Oculus: A Digital Twin Approach to BOP Reliability
Amine Meziou - Aquila Engineering
4:00 PM - 4:40 PM
A Low-Cost Solution to a High-Cost Problem: Artificial Intelligence and Drones for Oil Spill Detection in RGB Data
  • How can a low-cost, robust, and easy-to-deploy method using drones and AI be deployed to replace costly and scarce satellite based oil spill detection?
  • Combining drone footage and visible light spectrum data together with Convolutional neural networks (CNN) models to detect and mark the boundaries of spills and slicks
Amir H. Behzadan - Texas A&M University
Zahra Ghorbani - Texas A&M University