SciML / SciML/ModelOrderReduction.jl
Non-Intrusive MOR using Neural Networks
Open
Nobody has claimed this yet.
- Dominant language
- Julia
- Stars
- 43
- Forks
- 8
- Avg merge
- 11h 47m
- Merged PRs (30d)
- 14
Description
The idea is simple enough :
- This learns the forcing function in the reduced space. (POD space for instance)
- System is allowed to evolve in the reduced space and projected back.
https://www.sciencedirect.com/science/article/pii/S0021999118301190
If I understand correctly, Lift and Learn from #3 and Operator inference (for the lack of a better term) could be bundled with this in a single module, with NN being a generic version of it. Am I missing something?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked paper and comparing the proposed non-intrusive MOR approach with Lift and Learn and Operator inference from issue #3. The issue names no files, tests, entry points, or acceptance criteria; clarify the intended module scope and integration before implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- hpc, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100