Full Main Conference Agenda

DAY 1: ROI Business Cases To Justify Investment In Machine Learning & AI > Establishing Where It Provides The Greatest Value > Practical Application Case Studies To Optimize Production Efficiency > Predict Failure & Improve Equipment Reliability > Optimize Internal Workflows

8:50 Chair's Opening Remarks

ESTABLISHING THE BUSINESS CASE FOR MACHINE LEARNING & AI

< Assess The Cost vs. Value Of AI, Based On Size Of Operation & Short-Term, Imminent Business Priorities Of E&P Enterprises >

9:00 Demonstrating The ROI And Understanding 'What's Possible' With AI To Justify Investment In The Latest Machine Learning Innovations

While some E&P companies are figuring out how to get started, others are beginning to establish their AI and Machine Learning programs, whereas some leading major players have multiple on-going, successful projects and have evolved in well-run businesses, focussing on optimizing operational efficiency and maximizing margins. With so many disruptive technologies and innovative tools, technologies, hardware and software systems available, recurring questions being asked now are...
'What is the true ROI of Machine Learning?'

What are the bottom line benefits? What's possible? What's the real value?

>> This keynote panel discussion lifts ambiguities, deliver justifications and real-world use cases based on company size, to enable operators to justify investment in Machine Learning and AI.

  • Examine key business and performance metrics that provide high evidence of ROI to justify Machine Learning investment
  • Sharing insights on the real CapEx and OpEx reduction opportunities for different Machine Learning, Deep Learning and AI technologies to ensure you're getting your money's worth
  • Understand the extent of innovation that was undertaken and how investment decisions were made and justified
  • Evaluate the immediate-term payback of employing Machine Learning across the enterprise
  • Assess granular details to see what worked: Did the actual results correlate with projections made?
  • Understand how these operators are achieving business benefits and how they are collaborating across different business silos

Alexander Klebanov, Data Scientist, Chesapeake Energy

Mark Reynolds,  Digital Transformation Engineer, Formerly Southwestern Energy

Jeff Cornelius, EVP ICS Solutions, Darktrace

9:30 Question & Answer Session

WHERE DOES MACHINE LEARNING PROVIDE THE GREATEST VALUE?

KNOW WHERE THE REAL OPPORTUNITIES EXIST

< Focus Your Attention And Investment On Bigger Opportunities First & Maximize ROI >

9:40 Key Insight On When And Where To Implement The Latest Disruptive AI Technologies, Including Machine Learning: Generate Maximum In Key Operational Areas

The recent influx of Machine Learning and AI technologies means the opportunity to process numerous real-time data sets, every minute of every day, and build models where you are able to quantify change and achieve even bigger cost savings, is now within reach. That said, operators do not want to spend a lot of time and money doing analytics on things that are not really important and areas where real value is not being created.

  • What's costing the most money? Production, Drilling or Completions?
  • Where are operators finding the most savings when using predictive analytics and Machine Learning?
  • Where are operators seeing the quickest pay-off?
  • Where are operators seeing the greatest successes?

>> Get a 360* degree view on how to best utilize the latest disruptive technologies, including Machine Learning, to extract maximum value in key upstream areas of operation.

Jacob Melton, Data Scientist, Devon Energy

10:10 Question & Answer Session

10:20 Morning Refreshments In The Exhibition Area

DEEP-DIVE INTO WHAT HAS BEEN ACCOMPLISHED USING MACHINE LEARNING

OVERCOME UPSTREAM ENGINEERING & PERFORMANCE CHALLENGES

< Propel The Next Round Of Innovation To Increase Operational Efficiency, Find Process Bottlenecks And Achieve Additional Cost Savings >

Upstream E&P decision-makers are not interested in the theoretical side of Machine Learning. Whether it is Production, Drilling and/or Completions, executive level decisions makers need to see 'How Machine Learning applies to day-to-day operations'

10:50 Best-In-Class Strategies For Implementing Operational Artificial Intelligence And Machine Learning In Day-To-Day Operations: Successes & Lessons Learned

  • Access cutting-edge insight into the practical application of innovative systems, and fully understand their limitations and successes
  • Clarify the cost trade-offs and short and long-term value-gains from an improved, integrated analytics and Machine Learning program
  • Find out which are the right data-sets to prioritize, compare and analyze to build Machine Learning models
  • Assess where the real value opportunities are - production, drilling or completions - to further improve operational efficiency through advanced analytics

Huz Ismail, Data Scientist, Murphy Oil

Sean Aslam, Senior Data Science Analyst, Murphy Oil

11:20 Question & Answer Session

11:30 Examine How To Effectively Set Up A Designated Machine Learning Program To Improve Operations

Marcus Keenan, Hydrozonix

11:50 Question & Answer Session

OPTIMIZING PRODUCTION PERFORMANCE AND EFFICIENCY

USING ADVANCED PREDICTIVE ANALYTICS & MACHINE LEARNING CAPABILITIES

USE CASE 1: IMPROVE WELL PRODUCTIVITY & PERFORMANCE

12:00 Learn How To Apply Machine Learning To Know Exactly What Each Well Is Producing & Extract Maximum Well Intelligence To Be More Productive

  • What if your platform was able to tell you exactly what your well count is what each well is producing? How would you use that intelligence to plan better and recover more oil?
  • What if there was a way of predicting ahead of time how much production will increase/decrease by if you made choke changes?
  • Detecting well liquid loading for intervention & optimization
  • Using computer vision to automatically extract information from images

This presentation takes a look at real-world use cases that demonstrate how Machine Learning Models combined with an intelligent E&P actions can be used to optimize production efficiency, and increase well productivity and make operations more efficient.

Johnathan Hottell, SCADA Supervisors, EXCO Resources

12:30 Question & Answer Session

USE CASE 2: OPTIMIZE ARTIFICIAL LIFT CYCLE-TIME

12:40 Networking Lunch In The Exhibition Area

13:40 Learn How To Establish The Optimum Frequency And Cycle-Time Of Artificial Lift Equipment Using Machine Learning Models

Sharing a proven strategy for seamless integration of Machine Learning and AI into your operation, to drive Artificial Lift cycle-times and efficiency, with key insight on how to:

  • Calculate how many times a day and when you really need to run your artificial lift
  • Analyze existing production and well data and calculate the optimum time based on that
  • Learn how to automate the opening of valves or auto start of compressors

Mark Reynolds, Principle Architect Digital Transformation, Southwestern Energy

14:10 Question & Answer Session

USE CASE 3: DETECT ANOMALIES ON ARTIFICIAL LIFT EQUIPMENT

14:20 Applying Machine Learning Analytics To Detect Scale, Paraffin And Corrosion Build-Up On Artificial Lifts: Pre-Empt Failure And Eliminate Unplanned Downtime

  • Analyze how surface equipment failures can be predicted and pre-empted using Machine Learning intelligence
  • Determine how to use analytics to reduce the occurrence of breakdown and maintenance issues in the field and mitigate the risk of production downtime
  • Examine the ability of Machine Learning to predict anomalies when something is not functioning right

Yuechen Li, Reservoir Engineer, Marathon Oil

Alexander Klebanov, Data Scientist, Chesapeake Energy

14:50 Question & Answer Session

USE CASE 4: OPTIMIZE CHEMICAL USAGE

15:00 Sharing AI Best Practices To Predict When And How Much Chemicals Are Needed To Reduce Overall Usage And Keep Cost Down

  • Assess success stories of AI and its ability to predict chemical requirements in relation to well needs
  • Sharing dollar-driven results to establish cost savings that can be achieved by delivering chemicals only when needed, based on true data
  • Assess the pros and cons of monitoring vs. not monitoring and the cost savings associated with that

15:30 Question & Answer Session

15:40 Afternoon Refreshments In The Exhibition Area

FAILURE PREDICTION & EQUIPMENT RELIABILITY

USING MACHINE LEARNING TO > DETECT FAILURES AHEAD OF TIME > ELIMINATE UNPLANNED DOWNTIME > KNOW EXACTLY WHEN TO PERFORM MAINTENANCE & SAVE COST

For an E&P with 1000s of wells spread over a field, with some operated manually and others fully automated, striking the balance between going out and checking wells
physically for functionality, reliability and repair can be an arduous and costly task. This section of presentations focuses on how Machine Learning models can help operators to:

<< Predict Failures Ahead Of Time And Optimize Maintenance Schedules >>

PREDICT EQUIPMENT FAILURE

16:10 Learn How To Predict And Eliminate Equipment Failure Ahead Of Time Using Machine Learning

Learn from the experience of this operator and find out how to:

  • Assess how historical data is used to train a model using statistics to predict what your future will look like
  • Examine the ability of Machine Learning to predict anomalies when something is not functioning right
  • Learn how to detect failure tendencies and find failures before they occur

Mohammad Evazi Yadecuri, Data Scientist, California Resources Corporation

16:40 Question & Answer Session

IMPROVE EQUIPMENT RELIABILITY

16:50 Know Exactly When To Perform Maintenance And On Which Equipment Using Machine Learning Models: Reduce Maintenance Time & Cost And Unplanned Downtime

This real-world case study delivers key insight to:

  • Assess ways to see repeat failure patterns using Machine Learning
  • Know the frequency of remedial action and servicing
  • Determine when servicing needs to be carried out

Mohammad Evazi Yadecuri, Data Scientist, California Resources Corporation

17:20 Question & Answer Session

LEVERAGE AI & MACHINE LEARNING FOR INTERNAL WORKFLOW OPTIMIZATION

OPTIMIZE INTERNAL WORKFLOWS

17:30 Learn How To Leverage Artificial Intelligence As A Mechanism For Internal Workflow Management

  • Navigate the bottleneck of existing workflows and processes by implementing new, disruptive technologies
  • Demonstrating the value of artificial intelligence to make workflows that much more efficient
  • Showcasing how to use Machine Learning to streamline hauling and reduce driving hours and trips made
  • Real world examples on how operators have controlled and optimized workflows to gain efficiencies

Ryan Stalker, Change Management & Organizational Development Specialist, Williams

Rob Graham, Controls Technology Specialist, Williams

18:00 Question & Answer Session

18:10 Chair's Closing Remarks

18:20 - 19:20 Networking Drinks In The Exhibition Area

DAY 2: Overcome The Full Horizon Of Data Science Challenges > Real-Time Drilling & Completions Optimization Using Artificial Intelligence > Solve Exploration & Reservoir Challenges > Change Management & 'Skills Transformation Strategies

8:50 Chair's Opening Remarks

EMBRACE HOW TO COLLECT, USE & PROFIT FROM DATA

USING MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE

Machine Learning is making it easier for operators to generate value from data, but there is no data science in machine learning without good data to start with. Machine Learning Models can only be applied after different data sources are integrated, but...
Where does the industry stand with data integration?
What does it take to get value out of data of varying qualities and fidelities? How can you overcome the hurdle of handing large volumes of data & build models?

This opening keynote panel discussion kicks off with...

9:00 Part 1) An Industrial Immune System: AI Cyber Defense for OT Environments

  • How new AI algorithms are automating OT, ICS, sensor and IoT threat detection
  • Why 100% visibility allows you to preempt emerging situations
  • How automation can assist your security team to stay ahead of unknown attacks
  • Real-world examples of detected OT & IoT threats
  • Detect malicious & accidental insiders and sophisticated threat-actors

Jeff Cornelius, EVP ICS Solutions, Darktrace

9:25 Part 2) Knowledge Exchange Between Operators And Vendors On How To Overcome The Full Horizon Of Data Science Challenges, including...

  • Mixing Data of Different Quality & Fidelity: Find out how are you going to mix data that have different levels of noise on them
  • Making High-Grading Decisions: Learn how make your model intelligent enough to figure out which is the best suggestion out of all options
  • Data Usage: Understand the full range of possibilities on how to use production, drilling or completions data
  • Managing Data Resolutions: Find out how to use Edge technology and provide much better data for your enterprise
  • Data Ownership & Security: Find out how to manage the data ownership and security challenge
  • Data Transfer & Connectivity: Hear insight on what systems are being used to transfer data securely across large fields
  • Data Storage: Assess best approaches to store data securely

Jacob Melton, Data Scientist, Devon Energy

David Benham, Data Scientist, Chesapeake Energy

Todd Heitmann, Director Of Engineering Technology, Echo Energy

10:00 Question & Answer Session

10:10 Discuss Ways To Integrate The Whole Water Management Lifecycle Into One System To Improve Operational Control & Communication

Mark Patton, President, Hydrozonix

10:35 Question & Answer Session

10:40 Morning Refreshments In The Exhibition Area

REAL-TIME DRILLING OPTIMIZATION USING ARTIFICAL INTELLIGENCE

OPTIMIZE DECISIONS ON DRILL BIT TRAJECTORY, GEOSTEERING & LATERAL LENGTH

REAL-TIME DRILLING OPTIMIZATION

11:10 Leverage Real-Time Drilling Intelligence Using AI Tools To Make Drilling Operation Faster And More Efficient

This presentation will review the critical questions that operators are asking on the use of Machine Learning and deliver complete clarity on using AI tools to:

  • Learn how densely you can drill before you start to have strongly diminishing returns on your investment
  • Optimize the angle of a drill bit in real- time and improve your drill bit trajectory
  • Predict the best way to drill in a certain area
  • Geosteer the well, improve and drain the reservoir better

11:40 Question & Answer Session

OPTIMIZING WELL DESIGN & COMPLETIONS USING MACHINE LEARNING

USING DATA SETS TO IMPROVE WELL SPACING & COMPLETIONS DESIGN DECISIONS

IMPROVE WELL DESIGN & COMPLETIONS DECISIONS

11:50 Sharing Real-World Use Cases To Demonstrate The Value Of Data Science And Machine Learning To Optimize Well Design And Improve Completions Decisions

This case study will deliver key completions-specific lessons to derive maximum value from your Machine Learning program including:

  • Lessons on how an operator optimized completions based on small data sets
  • Decisions on how tightly wells can be packed/spaced before reserves start to get lost and the optimum spacing requirements
  • Alternatives on how to frac wells once they have been drilled

12:20 Question & Answer Session

12:30 Networking Lunch In The Exhibition Area

IMPROVE EXPLORATION, RESERVOIR SIMULATION & SEISMICITY

USING ARTIFICIAL INTELLIGENCE AND DEEP LEARNING

SOLVE EXPLORATION & RESERVOIR CHALLENGES

13:30 Assess How To Solve Upstream Exploration, Reservoir Simulation And Seismicity Challenges Using Machine Learning And Deep Learning

With this being one of the least explored and most challenging areas in upstream Oil & Gas, this presentation gives you real-world insight to understand how intelligent software systems can support exploration, reservoir development and seismicity management, including decisions on:

  • Determining sweet spots in a much more insightful manner than ever before
  • Automatically make adjustments to produced water injection volumes
  • Alleviate seismic activity using Machine Learning
  • Solving upstream challenges in geosciences, geology geophysics and reservoir simulations

14:00 Question & Answer Session

'CHANGE MANAGEMENT' & 'SKILLS TRANSFORMATION'

BEST PRACTICES FOR MANAGING EMPLOYEE BUY-IN, TRAINING INTERNAL STAFF

< Leverage The Advantages Of Machine Learning Rapidly, With 100% Staff Buy-in>
CHANGE MANAGEMENT STRATEGIES

14:10 Learn How A Leading Operator Has Incorporated Machine Learning & AI To Increase Operational Efficiencies While Achieving 100% Employee Buy-In

  • Fully understand the implications of implementing machine learning and AI on the your workforce
  • Sharing lessons learned for managing the status quo challenge and field employee's mind-sets
  • Understand how to overcome the fear of job cuts and general trust issues - the biggest pushback AI and machine learning gets from non-automation trained operators

Ryan Stalker, Change Management & Organizational Development Specialist, Williams

Rob Graham, Controls Technology Specialist, Williams

14:40 Question & Answer Session

OVERCOME THE 'SKILLS TRANSFORMATION' CHALLENGE

14:50 Practical Steps To Educate & Train Internal Employees To Leverage The Benefits Of Machine Learning, Rapidly And Without External Support

  • Learn how to deliver base knowledge on machine learning and AI as the first step in the right direction
  • Understand practical measures to educate employees on the value of Machine Learning and AI
  • Demonstrating how evidence of improved operational efficiency can make buy-in quicker and easier

David Benham, Data Scientist,Chesapeake Energy

Ryan Stalker, Change Management & Organizational Development Specialist, Williams

15:20 Question & Answer Session

15:30 Afternoon Refreshments In The Exhibition Area

ADVANCED APPLICATION OF MACHINE LEARNING

DEMONSTRATING THE TRUE POWER OF MACHINE LEARNING

ADVANCED MACHINE LEARNING CASE STUDY

16:00 Sharing Pilot Results On How E&Ps Have Seamlessly Applied AI And Machine Learning Across Key Operational Areas To Increase Production And Efficiency

See what the future of Machine Learning, AI and Digital Transformation is going to look like with this closing presentation. As majors and super majors work towards leveraging the full potential and true power of the latest disruptive technologies, this presentation gives you the opportunity to take back lessons learned and real-world success stories to work towards improving your current operation.

  • Discover how the trials were initiated and how they have come to be: what were the successes, issues and challenges encountered during the trials?
  • Learn how often adjustments were made on the back-end and how these small changes influenced results on the front-end
  • Hear how networks were set up with third parties without compromising security
  • Calculate the value added and efficiency gains through fully integrating Machine Learning into day-to-day operations

Jim Sokolowski, Senior Technical Consultant & Operations Manager, Tessella

16:30 Question & Answer Session

ROBUST MACHINE LEARNING TECHNOLOGIES AND COST-EFFECTIVE AI SOFTWARE

TECHNICAL CAPABILITIES & LIMITATIONS FOR APPLICATION IN HARSH ENVIRONMENTS

There is a lot of confusion about the capabilities and about the limitations of Machine Learning. A lot of decision makers don't exactly know what to expect and what they will get for their money when they launch one of a projects or when they create an analytics team. This section of presentations gives operators the chance to understand technical capabilities and limitations of disruptive applications, and vendors the opportunity to...

< Bridge The Gap Between Capability Promised And Value Delivered >
COST-EFFECTIVE MACHINE LEARNING TECHNOLOGIES

16:40 Assess The Functionalities And Limitations Of Systems That Are Capable Of Machine Learning To Determine Practical, Cost-Effective Options For Large And Small Operators

  • Showcasing cost and economics for new Machine Learning technologies
  • Understand the capabilities of new technologies and what they can be used for
  • Assess the cost/benefits of hardware systems that are capable of deep and
    Machine Learning
  • Evaluate innovative capabilities of Edge devices to perform data analytics out in
    the field level

Ricardo Vilalta, Associate Professor, University of Houston

17:10 Question & Answer Session

17:20 Chair's Closing Remarks

17:30 End Of Machine Learning & AI Upstream Onshore Oil & Gas 2018

JOIN OUR MAILING LIST

By continuing to use this site you agree to the use of cookies. For more information and to find out how to change this click here