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
06a: Room 2, Thursday 25th June 08:00 - 08:03
Nikolaos Prasianakis
View abstracts at 3 conferences in series
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.
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.