Deep Learning/Machine Learning Technical Interest Group (TIG)

Applying new analytics, neural networks, computational approaches using structured and unstructured data, and also training neural networks with supervised and unsupervised algorithms. Chaired by Patrick Ng and Andrew Munoz.
Deep Learning - Machine Learning TIG
PrevPrev Go to previous topic
NextNext Go to next topic
Last Post 18 Mar 2020 07:13 PM by  Patrick Ng
Risk averse - to be, or not to be
 0 Replies
Join to post a reply.
Author Messages
Patrick Ng
New Member
New Member

18 Mar 2020 07:13 PM
    In 2019, over a series of AAPG Analytics / Machine Learning Workshops across different regions, I posed this question to participants, “would you be ready to fly on 737 Max when it re-enters service?” In sessions attended by mostly engineers and data scientists, fewer than three hands were raised. However, in one hosted by the Kansas Geological Survey, half a dozen participants raised theirs. Interpretation? It may be attributable to professional mindsets, e.g., geologists more explorationist (risk takers) and engineers more measured (risk averse). More data will yield a better example.

    Data example? It so happened exactly one week ago. Houston Rodeo, a three-week major event, was cancelled after nine days on March 11 because of the coronavirus. Before cancellation, 8,000 petitioned online to cancel amidst Covid-19. Day after cancellation, 20,000 went online to petition Rodeo re-open. Perhaps it reflected a Texas state of mind, or perspective on the risk of being infected, i.e., “abundance of caution” vs “herd immunity”.

    What is clear is that there is not a single surefire answer. Response really depends on the risk tolerance and where you land on risk-reward trade off. That is not a theoretical question amidst the oil price plunge to the lowest level in eighteen years.

    Food for thought on machine learning applications:

    1) tackling the Parent-Child well interference (frac hit), and 2) while we cannot predict commodity prices, how about closing the “gap” between expectation and actual production on Shale wells?

    Call for action - as a community, lets do what we do best, e.g., share relevant experience in this TIG, and together better enable the industry to thrive in volatility and lower for longer WTI.
    Join to post a reply.


    Andrew Munoz Ensign Natural Resources
    Patrick Ng Real Core Energy

    Headquarters Contacts

    Susan Nash Director, Innovation and Emerging Science and Technology AAPG