Machine-learning emulators for reionization science
Turn expensive reionization simulations into fast, uncertainty-aware emulators, then serve them through a production inference API. Explore parameter space without rerunning the physics.
Python package
reionemu
Condense simulation outputs, compute summary statistics, assemble training datasets, and train uncertainty-aware emulators that predict observables from reionization parameters.
Documentation
Inference platform
Platform
Production inference for trained emulators: HTTP APIs, asynchronous jobs, and cloud deployment built on top of the package.
Under ConstructionPublications
If reionemu contributes to work you publish, please cite both the specific software release you used and any relevant papers listed below. Each release is archived with its own DOI, so the exact version you ran stays citable.
-
Paper
An Uncertainty-Aware Machine Learning Emulator for the Reionisation kSZ Power Spectrum
-
Software
reionemu: Python package for emulating the kSZ angular power spectrum from reionization simulations