Mochinaga et al, Probabilistic Approach for 3D Conceptual Modelling Using Multi Geophysical Data #6
EvanBianco
started this conversation in
WGC Awesome
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Abstract
YouTube
The keywords in the abstract: : 3D Conceptual Modelling, Artificial Neural Networks, Seismic Attributes, Bayesian Classification.
Unfortunately no data or code, but there is a whole gallery of geophysical techniques on display. And it has 3D seismic invovled which is in my comfort zone.
I like the notion of trying to integrate 3D seismic attributes into some kind of predictive model of temperature, caprock, feedzones etc. But this suffers from many other reservoir characterization works.
Is Test Well C (presumably a validation well) a "good" estimate of temperature or "bad"?
The thing that worries me is that you can do all the modeling you want away from the wells, but if you can't get "good enough" accuracy at the well locations (ground truth), then that throws everything else into question. I'm probably over simplifying it, but I feel like the rest of the workflow overshadows the implication of this metric. Thoughts?
All reactions