UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Benchmarking and scalability of machine-learning methods for photometric redshift estimation

Henghes, Ben; Pettitt, Connor; Thiyagalingam, Jeyan; Hey, Tony; Lahav, Ofer; (2021) Benchmarking and scalability of machine-learning methods for photometric redshift estimation. Monthly Notices of the Royal Astronomical Society , 505 (4) pp. 4847-4856. 10.1093/mnras/stab1513. Green open access

[thumbnail of Henghes_Benchmarking and scalability of machine-learning methods for photometric redshift estimation_VoR.pdf] Text
Henghes_Benchmarking and scalability of machine-learning methods for photometric redshift estimation_VoR.pdf - Published Version

Download (2MB)

Abstract

Obtaining accurate photometric redshift (photo-z) estimations is an important aspect of cosmology, remaining a prerequisite of many analyses. In creating novel methods to produce photo-z estimations, there has been a shift towards using machine-learning techniques. However, there has not been as much of a focus on how well different machine-learning methods scale or perform with the ever-increasing amounts of data being produced. Here, we introduce a benchmark designed to analyse the performance and scalability of different supervised machine-learning methods for photo-z estimation. Making use of the Sloan Digital Sky Survey (SDSS – DR12) data set, we analysed a variety of the most used machine-learning algorithms. By scaling the number of galaxies used to train and test the algorithms up to one million, we obtained several metrics demonstrating the algorithms’ performance and scalability for this task. Furthermore, by introducing a new optimization method, time-considered optimization, we were able to demonstrate how a small concession of error can allow for a great improvement in efficiency. From the algorithms tested, we found that the Random Forest performed best with a mean squared error, MSE = 0.0042; however, as other algorithms such as Boosted Decision Trees and k-Nearest Neighbours performed very similarly, we used our benchmarks to demonstrate how different algorithms could be superior in different scenarios. We believe that benchmarks like this will become essential with upcoming surveys, such as the Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST), which will capture billions of galaxies requiring photometric redshifts.

Type: Article
Title: Benchmarking and scalability of machine-learning methods for photometric redshift estimation
Open access status: An open access version is available from UCL Discovery
DOI: 10.1093/mnras/stab1513
Publisher version: https://doi.org/10.1093/mnras/stab1513
Language: English
Additional information: This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
Keywords: Science & Technology, Physical Sciences, Astronomy & Astrophysics, methods: data analysis, galaxies: distances and redshifts, cosmology: observations, DIGITAL SKY SURVEY
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Physics and Astronomy
URI: https://discovery.ucl.ac.uk/id/eprint/10160343
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item