SKATR: A Self-Supervised Summary Transformer for SKA

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ore, Ayodele, Heneka, Caroline, Plehn, Tilman
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915286864625664
author Ore, Ayodele
Heneka, Caroline
Plehn, Tilman
author_facet Ore, Ayodele
Heneka, Caroline
Plehn, Tilman
contents The Square Kilometer Array will initiate a new era of radio astronomy by allowing 3D imaging of the Universe during Cosmic Dawn and Reionization. Modern machine learning is crucial to analyse the highly structured and complex signal. However, accurate training data is expensive to simulate, and supervised learning may not generalize. We introduce a self-supervised vision transformer, SKATR, whose learned encoding can be cheaply adapted for downstream tasks on 21cm maps. Focusing on regression and generative inference of astrophysical and cosmological parameters, we demonstrate that SKATR representations are maximally informative and that SKATR generalises out-of-domain to differently-simulated, noised, and higher-resolution datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18899
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SKATR: A Self-Supervised Summary Transformer for SKA
Ore, Ayodele
Heneka, Caroline
Plehn, Tilman
Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
High Energy Physics - Phenomenology
The Square Kilometer Array will initiate a new era of radio astronomy by allowing 3D imaging of the Universe during Cosmic Dawn and Reionization. Modern machine learning is crucial to analyse the highly structured and complex signal. However, accurate training data is expensive to simulate, and supervised learning may not generalize. We introduce a self-supervised vision transformer, SKATR, whose learned encoding can be cheaply adapted for downstream tasks on 21cm maps. Focusing on regression and generative inference of astrophysical and cosmological parameters, we demonstrate that SKATR representations are maximally informative and that SKATR generalises out-of-domain to differently-simulated, noised, and higher-resolution datasets.
title SKATR: A Self-Supervised Summary Transformer for SKA
topic Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2410.18899