caio-davi/PSO-PINN

Physics-Informed Neural Networks Trained with Particle Swarm Optimization

40
/ 100
Emerging

This project helps engineers and scientists more accurately solve complex physics problems modeled by partial differential equations using deep learning. It takes in your differential equation model and relevant data, and outputs a robust, more reliable solution with quantified uncertainty. Researchers and practitioners in fields like fluid dynamics, heat transfer, or materials science who use Physics-Informed Neural Networks (PINNs) will find this useful.

No commits in the last 6 months.

Use this if you are developing or applying Physics-Informed Neural Networks (PINNs) and are encountering issues with training stability, slow convergence, or require a better understanding of the uncertainty in your model's predictions.

Not ideal if you are looking for a general-purpose machine learning framework for problems not involving partial differential equations, or if you prefer pure gradient-based optimization without an ensemble approach.

computational-physics differential-equations scientific-machine-learning engineering-simulation uncertainty-quantification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

27

Forks

10

Language

Python

License

MIT

Last pushed

Sep 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/caio-davi/PSO-PINN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.