A Caltech Library Service

METAPHOR: a machine-learning-based method for the probability density estimation of photometric redshifts

Cavuoti, S. and Amaro, V. and Brescia, M. and Vellucci, C. and Tortora, C. and Longo, G. (2017) METAPHOR: a machine-learning-based method for the probability density estimation of photometric redshifts. Monthly Notices of the Royal Astronomical Society, 465 (2). pp. 1959-1973. ISSN 0035-8711.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


A variety of fundamental astrophysical science topics require the determination of very accurate photometric redshifts (photo-z). A wide plethora of methods have been developed, based either on template models fitting or on empirical explorations of the photometric parameter space. Machine-learning-based techniques are not explicitly dependent on the physical priors and able to produce accurate photo-z estimations within the photometric ranges derived from the spectroscopic training set. These estimates, however, are not easy to characterize in terms of a photo-z probability density function (PDF), due to the fact that the analytical relation mapping the photometric parameters on to the redshift space is virtually unknown. We present METAPHOR (Machine-learning Estimation Tool for Accurate PHOtometric Redshifts), a method designed to provide a reliable PDF of the error distribution for empirical techniques. The method is implemented as a modular workflow, whose internal engine for photo-z estimation makes use of the MLPQNA neural network (Multi Layer Perceptron with Quasi Newton learning rule), with the possibility to easily replace the specific machine-learning model chosen to predict photo-z. We present a summary of results on SDSS-DR9 galaxy data, used also to perform a direct comparison with PDFs obtained by the Le Phare spectral energy distribution template fitting. We show that METAPHOR is capable to estimate the precision and reliability of photometric redshifts obtained with three different self-adaptive techniques, i.e. MLPQNA, Random Forest and the standard K-Nearest Neighbors models.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Cavuoti, S.0000-0002-3787-4196
Brescia, M.0000-0001-9506-5680
Longo, G.0000-0002-9182-8414
Additional Information:© 2016 The Authors Published by Oxford University Press on behalf of the Royal Astronomical Society. Received: 09 May 2016. Revision Received: 09 November 2016. Accepted: 09 November 2016. Published: 14 November 2016. The authors would like to thank the anonymous referee for extremely valuable comments and suggestions. MB and SC acknowledge financial contribution from the agreement ASI/INAF I/023/12/1. MB acknowledges the PRIN-INAF 2014 Glittering kaleidoscopes in the sky: the multifaceted nature and role of Galaxy Clusters. CT is supported through an NWO-VICI grant (project number 639.043.308).
Funding AgencyGrant Number
Agenzia Spaziale Italiana (ASI)I/023/12/1
Istituto Nazionale di Astrofisica (INAF)UNSPECIFIED
Nederlandse Organisatie voor Wetenschappelijk Onderzoek (NWO)639.043.308
Subject Keywords:techniques: photometric, galaxies: distances and redshifts, galaxies: photometry
Issue or Number:2
Record Number:CaltechAUTHORS:20170324-075726160
Persistent URL:
Official Citation:S. Cavuoti, V. Amaro, M. Brescia, C. Vellucci, C. Tortora, G. Longo; METAPHOR: a machine-learning-based method for the probability density estimation of photometric redshifts. Mon Not R Astron Soc 2017; 465 (2): 1959-1973. doi: 10.1093/mnras/stw2930
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:75370
Deposited By: Ruth Sustaita
Deposited On:24 Mar 2017 16:42
Last Modified:09 Mar 2020 13:19

Repository Staff Only: item control page