SciML / SciML/NeuralOperators.jl

Implement U-FNO (U-Net Enhanced Fourier Neural Operator)

Open
#107 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 U-FNO, which adds U-Net-style encoder-decoder paths to the Fourier Neural Operator.

Reference

Description

U-FNO augments the standard FNO with U-Net-style skip connections and encoder-decoder paths operating in physical space, in addition to the spectral-domain Fourier layers. This improves the model's ability to capture multi-scale features, particularly for complex multiphase flow applications.

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

No files, tests, or entry points are named. Start by locating the existing Fourier Neural Operator implementation and read Wen et al.'s U-FNO paper to map the encoder-decoder paths, physical-space operations, and skip connections onto the project. Done means U-FNO is implemented and its behavior is validated against the repository's existing operator tests or examples.

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
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.