Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Neural networks in petroleum engineering: a case study

M A Vukelic, E N Miranda

    International Journal of Neural Systems
    |May 1, 1996
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Analytical solution of the mean field Ising model for finite systems.

    Journal of physics. Condensed matter : an Institute of Physics journal·2012
    Same author

    On the capacity of multilayer neural networks trained with backpropagation.

    International journal of neural systems·2000
    Same author

    How good are formal neurons for modelling real ones?

    Acta biotheoretica·1997
    See all related articles

    A multilayer neural network effectively identifies optimal oil reservoir layers for perforation, outperforming human experts and historical averages. Network architecture is key to achieving superior generalization capabilities in this application.

    Area of Science:

    • Petroleum Engineering
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Oil reservoir perforation is critical for production optimization.
    • Traditional methods rely on human expertise, which can be inconsistent.
    • Developing automated systems for perforation layer selection is an ongoing challenge.

    Discussion:

    • A multilayer neural network (NN) was developed for selecting oil reservoir layers for perforation.
    • Extensive testing of various NN architectures identified optimal designs for generalization.
    • The NN's performance was benchmarked against human experts and historical data.

    Key Insights:

    • The developed NN significantly outperforms human experts in perforation layer selection.
    • The network's achievements surpass the historical average performance in the designated test area.

    Related Experiment Videos

  • Performance improvements were observed with increased hidden neurons, though generalization did not scale similarly.

    • Outlook:

    • Further research can explore advanced NN architectures for enhanced reservoir management.
    • Integration of NNs into real-time drilling operations could revolutionize perforation strategies.
    • Investigating the trade-offs between learning and generalization in NNs for complex geological applications remains important.