Skip to content

Issue on diffphys-code-sol.- Reducing Numerical Errors with Neural Operators #39

Description

@Al-Ofek

Hi, trying to reproduce results using the colab notebook as-is, and seemed to notice an issue with the low-fidelity simulation inside phiflow. For some reason the output is dramatically different from the reference simulator, with no flow pattern, and appears to not vary in time:

Image

It seems to be related to the transition to phiflow 3.4, since running the same code with phiflow version 3.3 yields results closer to what is expected:

Image

Insight into what might be the cause would be appreciated, since I want to replicate a similar setup, and was having trouble with version 3.3.
Thanks!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions