SciML / SciML/NeuralOperators.jl
Implement Geometry-Informed Neural Operator (GINO)
Nobody has claimed this yet.
- Dominant language
- Julia
- Stars
- 41
- Forks
- 15
- Avg merge
- 13h 14m
- Merged PRs (30d)
- 12
Description
Summary
Implement GINO, a hybrid GNO + FNO architecture that uses signed distance function (SDF) geometry encoding for large-scale 3D PDEs.
Reference
- Li et al., "Geometry-Informed Neural Operator for Large-Scale 3D PDEs," NeurIPS 2023. arXiv:2309.00583
Description
GINO combines GNO (for irregular input/output grids) with FNO (for efficient spectral processing on regular latent grids). Input geometry is encoded via signed distance functions (SDFs). The architecture maps from irregular mesh → regular latent grid via GNO, processes with FNO layers, then maps back via GNO. Reports 26,000x speedup over GPU-based CFD solvers for automotive aerodynamics.
Depends on graph neural network support (GNNLux) and the existing FNO implementation.
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 existing FNO implementation and checking the stated GNNLux dependency. Trace the proposed irregular mesh → regular latent grid → FNO → irregular output flow, including SDF geometry encoding. Done means a GINO implementation covering this architecture for large-scale 3D PDE inputs and outputs.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 28/100