BerkeleyLab/fiats

A deep learning library for use in high-performance computing applications in modern Fortran

55
/ 100
Established

This project helps scientists and engineers working with complex computational models by training and deploying neural network 'surrogate models'. You provide scientific data and the tool generates a trained neural network that can quickly make predictions, dramatically speeding up simulations. This is designed for researchers and practitioners in computational science who need faster, more efficient model execution.

Use this if you need to accelerate computationally intensive scientific simulations by replacing parts of them with high-performance neural network models.

Not ideal if you are not working with Fortran or if your primary need is general-purpose deep learning outside of high-performance scientific computing.

computational-science scientific-modeling high-performance-computing physics-based-simulations numerical-methods
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

70

Forks

28

Language

Fortran

License

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BerkeleyLab/fiats"

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