ProMage: fast galaxy magnitudes emulation combining SED forward-modelling and machine learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tortorelli, Luca, Fischbacher, Silvan, Robotham, Aaron S. G., Nussbaumer, Céline, Refregier, Alexandre
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911130421559296
author Tortorelli, Luca
Fischbacher, Silvan
Robotham, Aaron S. G.
Nussbaumer, Céline
Refregier, Alexandre
author_facet Tortorelli, Luca
Fischbacher, Silvan
Robotham, Aaron S. G.
Nussbaumer, Céline
Refregier, Alexandre
contents We present ProMage, a feed-forward neural network that emulates the computation of observer- and rest-frame magnitudes from the generative galaxy SED package ProSpect. The network predicts magnitudes conditioned on input galaxy physical properties, including redshift, star formation history, gas and dust parameters. ProMage accelerates magnitude computation by a factor of $10^4$ compared to ProSpect, while achieving per-mille relative accuracy for $99\%$ of sources in the test set across the $g,r,i,z,y$ Hyper Suprime-Cam bands. This acceleration is key to enabling fast inference of galaxy physical properties in next-generation Stage IV surveys and to generating large catalogue realisations in forward-modelling frameworks such as GalSBI-SPS.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00150
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProMage: fast galaxy magnitudes emulation combining SED forward-modelling and machine learning
Tortorelli, Luca
Fischbacher, Silvan
Robotham, Aaron S. G.
Nussbaumer, Céline
Refregier, Alexandre
Astrophysics of Galaxies
Instrumentation and Methods for Astrophysics
We present ProMage, a feed-forward neural network that emulates the computation of observer- and rest-frame magnitudes from the generative galaxy SED package ProSpect. The network predicts magnitudes conditioned on input galaxy physical properties, including redshift, star formation history, gas and dust parameters. ProMage accelerates magnitude computation by a factor of $10^4$ compared to ProSpect, while achieving per-mille relative accuracy for $99\%$ of sources in the test set across the $g,r,i,z,y$ Hyper Suprime-Cam bands. This acceleration is key to enabling fast inference of galaxy physical properties in next-generation Stage IV surveys and to generating large catalogue realisations in forward-modelling frameworks such as GalSBI-SPS.
title ProMage: fast galaxy magnitudes emulation combining SED forward-modelling and machine learning
topic Astrophysics of Galaxies
Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2509.00150