Benchmarking and Scalability of Machine Learning Methods for Photometric Redshift Estimation

TL;DR

This paper benchmarks the performance and scalability of various machine learning methods for photometric redshift estimation using SDSS data, highlighting the importance of efficient algorithms for upcoming large-scale surveys.

Contribution

It introduces a comprehensive benchmark for evaluating machine learning algorithms' scalability and performance in photometric redshift estimation, including a new time-considered optimization method.

Findings

Random Forest achieved the lowest mean squared error (MSE = 0.0042).

Algorithms like Boosted Decision Trees and k-Nearest Neighbours performed similarly.

The benchmark demonstrates how different algorithms excel in various scenarios.

Abstract

Obtaining accurate photometric redshift estimations is an important aspect of cosmology, remaining a prerequisite of many analyses. In creating novel methods to produce redshift 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 photometric redshift estimation. Making use of the Sloan Digital Sky Survey (SDSS - DR12) dataset, 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 optimisation method, time-considered optimisation, 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 in terms of error with a mean squared error, MSE = 0.0042; however, as other algorithms such as Boosted Decision Trees and k-Nearest Neighbours performed incredibly similarly, we used our benchmarks to demonstrate how different algorithms could be superior in different scenarios. We believe benchmarks such as this will become even more vital with upcoming surveys, such as LSST, which will capture billions of galaxies requiring photometric redshifts.