NeuralPDE.jl and heat-pinn

NeuralPDE.jl is a general-purpose PINN framework that heat-pinn uses as a reference implementation or builds upon for the specialized case of 2D steady-state heat equations, making them complements in a hierarchical ecosystem where the former provides infrastructure and the latter demonstrates application.

NeuralPDE.jl
71
Verified
heat-pinn
45
Emerging
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 17/25
Stars: 1,175
Forks: 235
Downloads:
Commits (30d): 29
Language: Julia
License:
Stars: 172
Forks: 23
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About NeuralPDE.jl

SciML/NeuralPDE.jl

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Leverages symbolic PDE definitions via ModelingToolkit to automatically construct physics-informed loss functions, eliminating manual differentiation and constraint specification. Supports diverse equation types (ODEs, SDEs, RODEs, integro-differential equations) with advanced training techniques including quadrature strategies and adaptive weighting, while maintaining interoperability with Flux.jl, Lux.jl, and NeuralOperators.jl for flexible neural architecture selection and GPU acceleration.

About heat-pinn

314arhaam/heat-pinn

A Physics-Informed Neural Network to solve 2D steady-state heat equations.

Scores updated daily from GitHub, PyPI, and npm data. How scores work