SciML / SciML/NeuralOperators.jl

Implement Geometry-Informed Neural Operator (GINO)

Open
#115 0 comments 0 reactions 0 assignees View on GitHub

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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.