A Sparse Gaussian Process Framework for Photometric Redshift Estimation

Abstract

Accurate photometric redshifts are a lynchpin for many future experiments to pin down the cosmological model and for studies of galaxy evolution. In this study, a novel sparse regression framework for photometric redshift estimation is presented. Simulated and real data from SDSS DR12 were used to train and test the proposed models. We show that approaches which include careful data preparation and model design offer a significant improvement in comparison with several competing machine learning algorithms. Standard implementations of most regression algorithms have as the objective the minimization of the sum of squared errors. For redshift inference, however, this induces a bias in the posterior mean of the output distribution, which can be problematic. In this paper we directly target minimizing $\Delta z=(z_{\text{s}}-z_{\text{p}})/(1+z_{\text{s}})$ and address the bias problem via a distribution-based weighting scheme, incorporated as part of the optimization objective. The results are compared with other machine learning algorithms in the field such as Artificial Neural Networks (ANN), Gaussian Processes (GPs) and sparse GPs. The proposed framework reaches a mean absolute $\Delta z=0.0026(1+z_{\text{s}})$, over the redshift range of $0\le z_{\text{s}}\le 2$ on the simulated data, and $\Delta z=0.0178(1+z_{\text{s}})$ over the entire redshift range on the SDSS DR12 survey, outperforming the standard ANNz used in the literature. We also investigate how the relative size of the training set affects the photometric redshift accuracy. We find that a training set of \textgreater 30 per cent of total sample size, provides little additional constraint on the photometric redshifts, and note that our GP formalism strongly outperforms ANNz in the sparse data regime for the simulated data set.

References in corpus (13)

• The Eleventh and Twelfth Data Releases of the Sloan Digital Sky Survey: Final Data from SDSS-III
• EAZY: A Fast, Public Photometric Redshift Code
• The VIMOS Ultra-Deep Survey: ~10,000 galaxies with spectroscopic redshifts to study galaxy assembly at early epochs 2<z<~6
• The Zurich Extragalactic Bayesian Redshift Analyzer (ZEBRA) and its first application: COSMOS
• Estimating the Redshift Distribution of Faint Galaxy Samples
• Photometric redshift analysis in the Dark Energy Survey Science Verification data
• Redshift distributions of galaxies in the DES Science Verification shear catalogue and implications for weak lensing
• Robust Machine Learning Applied to Astronomical Datasets III: Probabilistic Photometric Redshifts for Galaxies and Quasars in the SDSS and GALEX
• A catalogue of photometric redshifts for the SDSS-DR9 galaxies
• Feature importance for machine learning redshifts applied to SDSS galaxies
• New Approaches To Photometric Redshift Prediction Via Gaussian Process Regression In The Sloan Digital Sky Survey
• GAz: A Genetic Algorithm for Photometric Redshift Estimation
• Accurate photometric redshift probability density estimation - method comparison and application

Cited by in corpus (44)

• Observational constraints on the merger history of galaxies since $z\approx 6$: Probabilistic galaxy pair counts in the CANDELS fields
• GPz: Non-stationary sparse Gaussian processes for heteroscedastic uncertainty estimation in photometric redshifts
• Euclid preparation: X. The Euclid photometric-redshift challenge
• When Gaussian Process Meets Big Data: A Review of Scalable GPs
• All-purpose, all-sky photometric redshifts for the Legacy Imaging Surveys Data Release 8
• HELP: The Herschel Extragalactic Legacy Project
• Photometric redshifts for the next generation of deep radio continuum surveys - I: Template fitting
• Evaluation of probabilistic photometric redshift estimation approaches for The Rubin Observatory Legacy Survey of Space and Time (LSST)
• The LOFAR Two-metre Sky Survey IV. First Data Release: Photometric redshifts and rest-frame magnitudes
• The LOFAR Two-Metre Sky Survey (LoTSS): VI. Optical identifications for the second data release
• LOFAR-Boötes: Properties of high- and low-excitation radio galaxies at $0.5<z<2.0$
• Photometric Redshift Estimation with a Convolutional Neural Network: NetZ
• Photometric redshifts for the next generation of deep radio continuum surveys - II. Gaussian processes and hybrid estimates
• Morpho-z: improving photometric redshifts with galaxy morphology
• MIGHTEE: the nature of the radio-loud AGN population
• Improving Photometric Redshift Estimation using GPz: size information, post processing and improved photometry
• A machine learning approach to galaxy properties: joint redshift-stellar mass probability distributions with Random Forest
• The Blind Implosion-Maker - Automated Inertial Confinement Fusion experiment design
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• A Fast, 2D Gaussian Process Method Based on Celerite: Applications to Transiting Exoplanet Discovery and Characterization
• The LSST-DESC 3x2pt Tomography Optimization Challenge
• Augmenting machine learning photometric redshifts with Gaussian mixture models
• Hybrid photometric redshifts for sources in the COSMOS and XMM-LSS fields
• Photometric redshift estimation of galaxies in the DESI Legacy Imaging Surveys
• Sacrificing information for the greater good: how to select photometric bands for optimal accuracy
• Photometric Redshift Estimation with Galaxy Morphology using Self-Organizing Maps
• Estimating dayside effective temperatures of hot Jupiters and associated uncertainties through Gaussian process regression
• Using Sparse Gaussian Processes for Predicting Robust Inertial Confinement Fusion Implosion Yields
• Herschel-ATLAS Data Release III: Near-infrared counterparts in the South Galactic Pole field -- Another 100,000 submillimetre galaxies
• Mixture Models for Photometric Redshifts
• The LOFAR Two-metre Sky Survey Deep Fields -- Data Release 1: IV. Photometric redshifts and stellar masses
• Machine learning synthetic spectra for probabilistic redshift estimation: SYTH-Z
• Machine Learning Classification to Identify Catastrophic Outlier Photometric Redshift Estimates
• A multi-band AGN-SFG classifier for extragalactic radio surveys using machine learning
• The sensitivity of GPz estimates of photo-z posterior PDFs to realistically complex training set imperfections
• Degradation analysis in the estimation of photometric redshifts from non-representative training sets
• PoPE: A population-based approach to model spatial structure of astronomical systems
• Pulsar B1237+25 Aberration/Retardation Analysis from Decimeter to Decameter Wavelength: Challenge to "Radius-to-Frequency Mapping"
• Deriving Photometric Redshifts using Fuzzy Archetypes and Self-Organizing Maps. II. Comparing Sampling Techniques Using Mock Data
• TOPz: Photometric redshifts using template fitting applied to the GAMA survey
• Photometric redshifts for the S-PLUS Survey: is machine learning up to the task?
• J-HERTz: J-PLUS Heritage Exploration of Radio Targets at z $<$ 5
• Machine learning analysis of Photometric data from the Dark Energy Survey
• Photometry on Structured Backgrounds: Local Pixelwise Infilling by Regression