Hostname: page-component-7b7567c8c-z4zkx Total loading time: 0 Render date: 2026-11-16T19:21:35.754Z Has data issue: false hasContentIssue false

How do we design data sets for Machine Learning astronomy?

Published online by Cambridge University Press:  01 August 2025

Renée Hložek*
Affiliation:
Dunlap Institute for Astronomy & Astrophysics, 50 St. George Street, Toronto ON M5S 3H4David A. Dunlap Department for Astronomy & Astrophysics, 50 St. George Street, Toronto ON M5S 3H4
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

Many problems in astronomy and physics lend themselves to solutions from machine learning methods for the detection and classification of astronomical signals, and model inference from those signals. The historic presentation of machine learning methods as ‘black boxes’ has generated push back from some in the the physics/astronomy communities regarding how useful they are to truly uncover the physical laws that govern our world. Skepticism about the applicability of new computational methods in scientific inference is not new; we highlight connections between the machine learning contexts and previous computational paradigm shifts in astronomy. Moreover, several advances in methodologies challenge the assumption that machine learning ‘gives us answers that we can use but do not understand’ to standing physics questions. We summarize some astronomical machine learning data challenges used in astronomy and how we can use challenges on different scales to test different parts/use cases of our analysis methods.

Information

Type
Contributed Paper
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of International Astronomical Union