Feature importance for machine learning redshifts applied to SDSS galaxies

Abstract

We present an analysis of importance feature selection applied to photometric redshift estimation using the machine learning architecture Decision Trees with the ensemble learning routine Adaboost (hereafter RDF). We select a list of 85 easily measured (or derived) photometric quantities (or `features') and spectroscopic redshifts for almost two million galaxies from the Sloan Digital Sky Survey Data Release 10. After identifying which features have the most predictive power, we use standard artificial Neural Networks (aNN) to show that the addition of these features, in combination with the standard magnitudes and colours, improves the machine learning redshift estimate by 18% and decreases the catastrophic outlier rate by 32%. We further compare the redshift estimate using RDF with those from two different aNNs, and with photometric redshifts available from the SDSS. We find that the RDF requires orders of magnitude less computation time than the aNNs to obtain a machine learning redshift while reducing both the catastrophic outlier rate by up to 43%, and the redshift error by up to 25%. When compared to the SDSS photometric redshifts, the RDF machine learning redshifts both decreases the standard deviation of residuals scaled by 1/(1+z) by 36% from 0.066 to 0.041, and decreases the fraction of catastrophic outliers by 57% from 2.32% to 0.99%.

arXiv comment10 pages, 4 figures, updated to match version accepted in MNRAS

References in corpus (22)

• The Sloan Digital Sky Survey: Technical Summary
• The Seventh Data Release of the Sloan Digital Sky Survey
• The 2.5 m Telescope of the Sloan Digital Sky Survey
• SDSS-III: Massive Spectroscopic Surveys of the Distant Universe, the Milky Way Galaxy, and Extra-Solar Planetary Systems
• The u'g'r'i'z' Standard Star Network
• The Ninth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Baryon Oscillation Spectroscopic Survey
• COSMOS Photometric Redshifts with 30-bands for 2-deg2
• The Tenth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Apache Point Observatory Galactic Evolution Experiment
• ANNz: estimating photometric redshifts using artificial neural networks
• A Critical Assessment of Photometric Redshift Methods: A CANDELS Investigation
• Slicing Through Multicolor Space: Galaxy Redshifts From Broadband Photometry
• TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
• The Zurich Extragalactic Bayesian Redshift Analyzer (ZEBRA) and its first application: COSMOS
• PHAT: PHoto-z Accuracy Testing
• Photometric redshift analysis in the Dark Energy Survey Science Verification data
• ArborZ: Photometric Redshifts Using Boosted Decision Trees
• Spectral Templates from Multicolor Redshift Surveys
• Creating Spectral Templates from Multicolor Redshift Surveys
• Photometric redshifts for Quasars in multi band Surveys
• A catalogue of photometric redshifts for the SDSS-DR9 galaxies
• The Efficacy of Galaxy Shape Parameters in Photometric Redshift Estimation: A Neural Network Approach
• Effect of Inclination of Galaxies on Photometric Redshift

Cited by in corpus (29)

• redMaGiC: Selecting Luminous Red Galaxies from the DES Science Verification Data
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• DNF - Galaxy photometric redshift by Directional Neighbourhood Fitting
• Photometric redshifts for the Kilo-Degree Survey. Machine-learning analysis with artificial neural networks
• METAPHOR: A machine learning based method for the probability density estimation of photometric redshifts
• A Sparse Gaussian Process Framework for Photometric Redshift Estimation
• Anomaly detection for machine learning redshifts applied to SDSS galaxies
• Separation of pulsar signals from noise with supervised machine learning algorithms
• GalaxyNet: Connecting galaxies and dark matter haloes with deep neural networks and reinforcement learning in large volumes
• Selection biases in empirical p(z) methods for weak lensing
• Improving Photometric Redshift Estimation using GPz: size information, post processing and improved photometry
• Photometric redshift estimation based on data mining with PhotoRApToR
• Star-galaxy classification in the Dark Energy Survey Y1 dataset
• Return of the features. Efficient feature selection and interpretation for photometric redshifts
• SED-dependent Galactic Extinction Prescription for Euclid and Future Cosmological Surveys
• Stacking for machine learning redshifts applied to SDSS galaxies
• GAME: GAlaxy Machine learning for Emission lines
• Comparing cosmic web classifiers using information theory
• Learning from the machine: interpreting machine learning algorithms for point- and extended- source classification
• Sacrificing information for the greater good: how to select photometric bands for optimal accuracy
• A Machine Learning Approach to Galaxy-LSS Classification I: Imprints on Halo Merger Trees
• Merged or monolithic? Using machine-learning to reconstruct the dynamical history of simulated star clusters
• Tuning target selection algorithms to improve galaxy redshift estimates
• Improved photometric redshifts with colour-constrained galaxy templates for future wide-area surveys
• The many flavours of photometric redshifts
• Cosmological Inference with Cosmic Voids and Neural Network Emulators
• Interpreting deep learning-based stellar mass estimation via causal analysis and mutual information decomposition
• Probability density estimation of photometric redshifts based on machine learning