Physics Informed Neural Networks Python Packages

pina-mathlab

Physics-Informed Neural networks for Advanced modeling

pinnicle

A general PINN framework for solving ice sheet modeling

parametrix

🪄 Flax-like computed parameters for bare JAX (and Equinox)

pinnx

Physics-Informed Neural Networks for Scientific Machine Learning in JAX

jwave

A JAX-based research framework for differentiable and parallelizable acoustic simulations, on CPU, GPUs and TPUs

neurodiffeq

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.

simulai-toolkit

A toolkit with data-driven pipelines for physics-informed machine learning.

marimo-flow

Reactive marimo notebooks for ML with MLflow tracking, PINA physics-informed neural networks, and a multi-agent team on pydantic-graph + Ollama Cloud.

tensordiffeq

Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing

pdebench

PDEBench: An Extensive Benchmark for Scientific Machine Learning

geoprior-v3

Physics-guided AI for geohazards

nops

nops is designed to be an elegant, high-level layer over complex neural operator architectures

pinnstorch

PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.

promethium-seismic

Promethium is a state-of-the-art, AI-driven framework for seismic signal reconstruction, denoising, and geophysical data enhancement, integrating cutting-edge deep learning architectures with production-grade data engineering.

pararealml

A machine learning boosted parallel-in-time differential equation solver framework.

idrlnet

IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural Network (PINN) systematically.

fast-poisson-solver

The Poisson equation is an integral part of many physical phenomena, yet its computation is often time-consuming. This module presents an efficient method using physics-informed neural networks (PINNs) to rapidly solve arbitrary 2D Poisson problems.

fastvpinns

FastVPINNs - A tensor-driven acceleration of VPINNs for complex geometries

oscillink

Oscillink — Self‑Optimizing Coherent Memory for Embedding Workflows

separable-operator-networks

Separable operator models for extreme-scale learning of parametric PDEs

pinnstf2

PINNs-TF2, Physics-informed Neural Networks (PINNs) implemented in TensorFlow V2.

physdbd

Physics-based machine learning with dynamic Boltzmann distributions

frontx

Nonlinear diffusion problems with JAX

pinnsjax

PINNs-JAX, Physics-informed Neural Networks (PINNs) implemented in JAX.