AAPG Workshop: Boosting Reserves and Recovery Using Machine Learning and Analytics

Please login to register for events. Go to the HGS home page and login with your user name and password and then return to this page in order to register as a member or guest of a member. For help registering contact the HGS office or email webmaster@hgs.org. Thank you!


This machine learning and analytics workshop is unique in that it focuses on applied analytics with specific, powerful outcomes. These analytics are coupled with real-world operational knowledge. This workshop is ideal for large, small, and medium-sized operators, along with innovative start-ups.

Workshop Goals

Boost recoverable reserves, reduce operating costs, evaluate acquisitions, use analytics to manage midstream operations and detect leaks.

List of Topics and Accepted Papers

Session 1

Big Data, Machine Learning, Deep Learning in Exploration and Production

Where do we use analytics in upstream?

Industrial Internet of Things in the oil field: What does it mean for the engineers, geologists, data scientists?

  • Supervised Learning Applied to Rock Type Classification in Sandstone Based on Wireline Formation Pressure Data, Jose Victor Contreras Sandia, Baker Hughes, a GE Company

  • Challenges faced with processing petrophysical big data for assessing viable opportunities, CJ Ejimuda, Hybrid Data Solutions

  • How I Transitioned from a Geologist to Data Scientist: Data Science from a Geologist's Perspective, Fuge Zou, Marathon

  • Geological Facies Prediction Using Computed Tomography in a Machine Learning and Deep Learning Environment, Uchenna Odi, Devon

  • A deep dive into automated switch point detection in estimating EUR's, Akash Sharma, DrillingInfo

Session 2

Analytics for Finding and Producing Hydrocarbons

Seismic imaging breakthroughs using deep learning, etc.

Attribute determination using deep learning

How can you make the new apps, data sources, platforms, etc. work for you?

  • Finding Hydrocarbons and estimating reserves using Neural Net Classification and Geobodies, Deborah Sacrey, Auburn Energy

  • Application of Data Science and Machine Learning for Well Completion Optimization, Piyush Pankaj, Schlumberger

  • Exploring for Wolfcamp reservoirs, Eastern Shelf of the Permian Basin, Texas, using a Machine Learning approach, Florian Basier, Emerson

  • Generate Structural Models in Real time using Artificial Intelligence (AI) while Drilling, Sunil Garg, DataVedik

  • Geologic - Reservoir 3D Characterization Modeling Used to Develop Analytic and Economic Outlook Models of Unconventional Resources, Onshore Continental United States, Bill Fairhurst, BEG

  • Predicting Potential Reservoirs in Shale Plays by DNA Fingerprinting and Machine Learning, Robert Chelak, Biodentify

Session 3

Predicting Fluid Behaviors in Reservoirs

Predicting fluid behaviors in drilling

Predicting fluid behaviors in completion

Predicting fluid behaviors in production

  • Deep QI: A Machine Learning Approach to Quantitative Interpretation Ehsan Naeini, IkonScience

  • Stochastic Realization of Parameter Inversion in Physics Based Empirical Models Srinivasan Jagannathan, Srinath Madasu, Oluwatosin Ogundare, Keshava Rangarajan, Halliburton

  • Deep Learning to Expand Productive Limits of Fields and Improve Production, Sashi Gunturu, Petrabytes

  • The Sparse Data Problem in Data Science, Giewee Hammond, Aramco Services Company

  • Synthetic Well Log Generation Using Machine Learning Techniques, Oyewande Akinnikawe, Devon

  • Machine Learning and Deep Learning for Risk Assessment, Susan Nash, AAPG

Session 4

Evaluations, Mergers, Acquisitions, Assessing Opportunities

Using new AI / machine learning for property evaluations

Machine Learning / Deep Learning and Enhanced Oil Recovery

Machine learning and solving water / emissions / disposal issues

Asset and Production Optimization using Dynamic Modeling

  • Field Assessment and Asset Management gets smarter with an AI Colleague, Sidd Gupta, Nesh

  • Robust Life-Cycle Production Optimization with a Support-Vector-Regression Proxy, Zhenyu Guo, Oxy

  • A comparison of multivariate models for predicting production, Patrick Rutty, Drilling Info

  • Drill down into the Risk and the Return, Patrick Ng, Real Core Energy

  • Domain Expertise in “Steroids” - O&G Experts enabled by AI-ML can break down barriers to enter and compete in The highly desire Delaware Basin, Leo Pirela, VPlusEnergy

  • Machine Learning in 4D Seismic Interpretation: Monitoring the Reservoir, Mike Brhlik, ConocoPhillips


Non-Member Fee $795

Member Fee $695

Student Fee $395

Speaker Fee $395

Affiliated Society/Displaced Worker Fee $395

Registration includes:

Daily Continental breakfast

Morning coffee breaks


Afternoon coffee breaks

Networking reception Day 1

Program book

Access to presentations

List of registrants

Select trial software licenses and tutorials


Visit the AAPG website for more information!


January 16th, 2019 8:00 AM   through   January 17th, 2019 4:00 PM
Speaker Info
Speaker Title
Speaker Company
Speaker Bio
Event Attachments
Speaker Lineup
Sponsorship Opportunities
Vendor Form
Additional Info
Additional Info 2
Additional Info 3
Additional Info 4
Event Contact
Contact Phone
contact Email

If this event is specific to a Committee, select the committee here, so the event will ONLY be listed on that committees calendar.

Event Filter Informations
Event Owner
Event Categories Non HGS
Event Image

Help spread the word

Please help us and let your friends, colleagues and followers know about our page: AAPG Workshop: Boosting Reserves and Recovery Using Machine Learning and Analytics

You can also share the below link in an email or on your website.