EEmGuzman/resunet-cmb

Code repository for the implementation of the ResUNet-CMB network from "Reconstructing Patchy Reionization with Deep Learning" (https://arxiv.org/abs/2101.01214), "Reconstructing Cosmic Polarization Rotation with ResUNet-CMB" (https://arxiv.org/abs/2109.09715), and "Deep Learning for Primordial B-mode Extraction" (https://arxiv.org/abs/2512.19577))

45
/ 100
Emerging

This project helps cosmologists and astrophysicists reconstruct key cosmic phenomena from Cosmic Microwave Background (CMB) polarization maps. You provide observed CMB Q and U polarization maps, and it outputs estimates of patchy reionization, lensing convergence, and primordial E-mode CMB polarization. It's designed for researchers studying the early universe and its subtle distortions.

Use this if you need to accurately separate and reconstruct patchy reionization, gravitational lensing, and primordial E-modes from noisy CMB polarization data.

Not ideal if you are not working with CMB polarization data or if you need to analyze phenomena outside of these specific cosmic distortions.

cosmology astrophysics CMB-analysis reionization-studies gravitational-lensing
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

7

Forks

5

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EEmGuzman/resunet-cmb"

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