Automated Spectral Classification of Galaxies using Machine Learning Approach on Alibaba Cloud AI platform (PAI)

TL;DR

This paper explores automated galaxy spectral classification using supervised machine learning algorithms on a large dataset from SDSS DR14, demonstrating the effectiveness of cloud-based AI tools in astronomy.

Contribution

It introduces a machine learning approach for galaxy spectra classification on Alibaba Cloud AI platform, comparing multiple algorithms for improved automation.

Findings

Random Forest achieved the highest accuracy among tested algorithms.

Supervised learning effectively classifies galaxy subclasses.

Cloud platform enables scalable spectral analysis.

Abstract

Automated spectral classification is an active research area in astronomy at the age of data explosion. While new generation of sky survey telescopes (e.g. LAMOST and SDSS) produce huge amount of spectra, automated spectral classification is highly required to replace the current model fitting approach with human intervention. Galaxies, and especially active galactic nucleus (AGNs), are important targets of sky survey programs. Efficient and automated methods for galaxy spectra classification is the basis of systematic study on physical properties and evolution of galaxies. To address the problem, in this paper we carry out an experiment on Alibaba Cloud AI plaform (PAI) to explore automated galaxy spectral classification using machine learning approach. Supervised machine learning algorithms (Logistic Regression, Random Forest and Linear SVM) were performed on a dataset consist of ~ 10000 galaxy spectra of SDSS DR14, and the classification results of which are compared and discussed. These galaxy spectra each has a subclass tag (i.e. AGNs, Starburst, Starforming, and etc.) that we use as training labels.