dpiras/cosmopower-jax

Differentiable cosmological emulators: the JAX version of CosmoPower

50
/ 100
Established

This tool helps cosmologists and astrophysicists analyze complex cosmological data more efficiently. It takes in cosmological parameters, such as the density of matter or the expansion rate of the universe, and quickly produces predictions of cosmological power spectra, which describe the distribution of matter and energy in the universe. This allows researchers to rapidly test hypotheses and explore a wide range of cosmic models.

Available on PyPI.

Use this if you need to perform high-dimensional Bayesian inference or generate quick, differentiable predictions of cosmological power spectra for research or analysis.

Not ideal if you need to train new JAX-based neural network models from scratch on custom data, as this functionality is not currently provided.

cosmology astrophysics Bayesian-inference power-spectrum-analysis universe-modeling
Maintenance 6 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 11 / 25

How are scores calculated?

Stars

45

Forks

5

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Nov 27, 2025

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dpiras/cosmopower-jax"

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