What is it about?
This article is at the intersection of astrophysics and artificial intelligence. Two-dimensional power-law relationships are used extremely frequently in astrophysics. We show machine learning can find more accurate relations in higher dimensions. Deep neural networks are powerful but not interpretable, we use a machine learning tool which models patterns in a dataset in the form of interpretable equations.
Featured Image
Photo by Graham Holtshausen on Unsplash
Why is it important?
Numerous upcoming observational surveys want to measure masses of clusters of galaxies in order to more accurately infer the fundamental properties of the Universe. Our new equations helps make the mass inference more accurate.
Perspectives
Deep neural networks are ubiquitously used to
Digvijay Wadekar
Institute for Advanced Study
Read the Original
This page is a summary of: Augmenting astrophysical scaling relations with machine learning: Application to reducing the Sunyaev–Zeldovich flux–mass scatter, Proceedings of the National Academy of Sciences, March 2023, Proceedings of the National Academy of Sciences,
DOI: 10.1073/pnas.2202074120.
You can read the full text:
Resources
Contributors
The following have contributed to this page
