Anomaly detection for machine learning redshifts applied to SDSS galaxies

TL;DR

This paper demonstrates that removing anomalous training examples from SDSS galaxy data significantly improves machine learning redshift estimation accuracy, with up to 80% better statistics.

Contribution

It introduces an anomaly detection method to identify and remove unreliable training data, enhancing machine learning redshift predictions for galaxies.

Findings

Up to 80% improvement in redshift estimation statistics

Effective use of Elliptical Envelope technique for anomaly detection

Method to estimate contamination fraction in data samples

Abstract

We present an analysis of anomaly detection for machine learning redshift estimation. Anomaly detection allows the removal of poor training examples, which can adversely influence redshift estimates. Anomalous training examples may be photometric galaxies with incorrect spectroscopic redshifts, or galaxies with one or more poorly measured photometric quantity. We select 2.5 million 'clean' SDSS DR12 galaxies with reliable spectroscopic redshifts, and 6730 'anomalous' galaxies with spectroscopic redshift measurements which are flagged as unreliable. We contaminate the clean base galaxy sample with galaxies with unreliable redshifts and attempt to recover the contaminating galaxies using the Elliptical Envelope technique. We then train four machine learning architectures for redshift analysis on both the contaminated sample and on the preprocessed 'anomaly-removed' sample and measure redshift statistics on a clean validation sample generated without any preprocessing. We find an improvement on all measured statistics of up to 80% when training on the anomaly removed sample as compared with training on the contaminated sample for each of the machine learning routines explored. We further describe a method to estimate the contamination fraction of a base data sample.