Photometric redshift estimation using Gaussian processes

Abstract

We present a comparison between Gaussian processes (GPs) and artificial neural networks (ANNs) as methods for determining photometric redshifts for galaxies, given training set data. In particular, we compare their degradation in performance as the training set size is degraded in ways which might be caused by the observational limitations of spectroscopy. We find that performance with large, complete training sets is very similar, although the ANN achieves slightly smaller root mean square errors. If the size of the training set is reduced by random sampling, the RMS errors of both methods increase, but they do so to a lesser extent and in a much smoother manner for the case of GP regression. When training objects are removed at redshifts 1.3<z<1.7, to simulate the effects of the "redshift desert" of optical spectroscopy, the GP regression is successful at interpolating across the redshift gap, while the ANN suffers from strong bias for test objects in this redshift range. Overall, GP regression has attractive properties for photometric redshift estimation, particularly for deep, high-redshift surveys where it is difficult to obtain a large, complete training set. At present, unlike the ANN code, public GP regression codes do not take account of inhomogeneous measurement errors on the photometric data, and thus cannot estimate reliable uncertainties on the predicted redshifts. However, a better treatment of errors is in principle possible, and the promising results in this paper suggest that such improved GP algorithms should be pursued. (abridged)

8 pages, 9 figures, accepted for publication in Monthly Notices of the RAS. This version is expanded to test additional observational biases which can affect training data

References in corpus (6)

• Accurate photometric redshifts for the CFHT Legacy Survey calibrated using the VIMOS VLT Deep Survey
• The Zurich Extragalactic Bayesian Redshift Analyzer (ZEBRA) and its first application: COSMOS
• Photo-z for weak lensing tomography from space: the role of optical and near-IR photometry
• Novel Methods for Predicting Photometric Redshifts from Broad Band Photometry using Virtual Sensors
• New Approaches To Photometric Redshift Prediction Via Gaussian Process Regression In The Sloan Digital Sky Survey
• Spectroscopic follow-up of a cluster candidate at z = 1.45

Cited by in corpus (23)

• TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
• Nonparametric Reconstruction of the Dark Energy Equation of State
• SOMz: photometric redshift PDFs with self organizing maps and random atlas
• GPz: Non-stationary sparse Gaussian processes for heteroscedastic uncertainty estimation in photometric redshifts
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Shedding Light on the Galaxy Luminosity Function
• A Sparse Gaussian Process Framework for Photometric Redshift Estimation
• Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification
• Morpho-z: improving photometric redshifts with galaxy morphology
• Measuring large-scale structure with quasars in narrow-band filter surveys
• Photometric Redshift Estimation of BASS DR3 Quasars by Machine Learning
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• Assessing the photometric redshift precision of the S-PLUS survey: the Stripe-82 as a test-case
• The PAU Survey: narrowband photometric redshifts using Gaussian processes
• Augmenting machine learning photometric redshifts with Gaussian mixture models
• Photometric redshift estimation of galaxies in the DESI Legacy Imaging Surveys
• Photometric Redshift Estimation with Galaxy Morphology using Self-Organizing Maps
• Galaxy Tagging: photometric redshift refinement and group richness enhancement
• Detection of Einstein Telescope gravitational wave signals from binary black holes using deep learning
• Conditional Neural Process for non-parametric modeling of AGN light curve
• Photo-$z$ with CuBAN$z$: An improved photometric redshift estimator using Clustering aided Back Propagation Neural network
• Degradation analysis in the estimation of photometric redshifts from non-representative training sets
• Data-Driven Sensitivity Inference for Thomson Scattering Electron Density Measurement Systems