Home

  • Site Map

    All the web pages on the conference website

Program

Events

Locations

Information

Exhibition

Sponsorships

My Goldschmidt

Role functions

Abstract Details

(2020) Towards Digital Twins: Machine Learning Based Process Coupling and Multiscale Modelling of Reactive Transport Phenomena

Prasianakis N

https://doi.org/10.46427/gold2020.2116

Sorry, the PDF cannot be displayed on your browser.

Download abstract

06a: Room 2, Thursday 25th June 08:00 - 08:03

Listed below are questions that have been submitted by the community that the author will try and cover in their presentation. To submit a question, ensure you are signed in to the website. Authors or session conveners approve questions before they are displayed here.

Submitted by Jenna Poonoosamy on Thursday 25th June 05:07
Could you please elaborate how the computational efficiency and memory requirements are improved? on slide 10-11: Did you consider only porosity as input for machine learning to access the permeability, the permeability also requires the consideration of surface area, dead end pores and other parameters, can the pictures be used as input for training? One can use a pore-scale model to calculate the effective permeability but the REV scale needs to be reached. Is the picture considered an REV representation such that the derrived porosity/permeability relationship is valid at the continuum scale.


Sign in to ask a question.

Goldschmidt® is a registered trademark of the Geochemical Society and of the European Association of Geochemistry

Website managed and hosted by White Iron Conferences on behalf of the international geochemical community