# neuraloperator/neuraloperator

Learning in infinite dimension with neural operators.

Repository: https://github.com/neuraloperator/neuraloperator
Canonical: https://ross.abutalabs.com/products/neuraloperator
Homepage: https://neuraloperator.github.io/dev/index.html
Language: Python
License: MIT
License Family: permissive
Topics: neural-operator, neural-operators, partial-differential-equations, pytorch, tensor-methods, fourier-neural-operator, fno, tensorly
Last push: 2026-08-06T00:52:41+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 53, longevity 100
- inputs: {"age_days": 2150, "days_push": 28, "days_rel": 315, "gap_med": 10, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3836, forks 919 (observed 2026-08-28T04:08:23.846694+00:00)

## What it is
A PyTorch library for learning neural operators, which map between function spaces rather than finite-dimensional vectors. It provides the official implementation of the Fourier Neural Operator (FNO) and related architectures, with resolution-invariant models for PDE learning.

## Use cases
- learn mappings between function spaces with neural networks
- solve partial differential equations with machine learning
- train a Fourier Neural Operator on my own data
- build PDE surrogates that work at any grid resolution
- compress FNO models with tensor factorization
- run scientific ML experiments on Darcy flow datasets

## When to choose
- you need resolution-invariant neural operators for PDE or physics problems
- you want the official, PyTorch-ecosystem FNO implementation
- you want tensorized (Tucker) variants to reduce model parameters
- you work in scientific machine learning with PyTorch

## When to avoid
- you need standard vision/NLP models rather than operator learning
- you prefer TensorFlow or JAX instead of PyTorch
- you need a no-code or GUI tool rather than a Python library

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, simulation, math
- domain: machine-learning, deep-learning, simulation, data-science
- platform: python
- tags: neural-operator, fourier-neural-operator, fno, pde, pytorch-ecosystem, scientific-machine-learning, tensor-factorization, gpu

## Member repositories
- neuraloperator/neuraloperator (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:23.846694+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:26:16.927470+00:00, confidence not recorded.
  - readme: https://github.com/neuraloperator/neuraloperator (fetched 2026-08-28T04:08:23.846694+00:00, sha 7259f20daaa2)
  - homepage: https://neuraloperator.github.io/dev/index.html (fetched 2026-08-29T09:20:57.772582+00:00, sha 9962bdf7b957)
- Data as of 2026-08-30T08:39:29.467469+00:00.