TY - JOUR

T1 - On the realistic validation of photometric redshifts

AU - Beck, R.

AU - Lin, C. A.

AU - Ishida, E. E.O.

AU - Gieseke, F.

AU - de Souza, R. S.

AU - Costa-Duarte, M. V.

AU - Hattab, M. W.

AU - Krone-Martins, A.

AU - COIN Collaboration

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Two of the main problems encountered in the development and accurate validation of photometric redshift (photo-z) techniques are the lack of spectroscopic coverage in the feature space (e.g. colours and magnitudes) and the mismatch between the photometric error distributions associated with the spectroscopic and photometric samples. Although these issues are well known, there is currently no standard benchmark allowing a quantitative analysis of their impact on the final photo-z estimation. In this work, we present two galaxy catalogues, Teddy and Happy, built to enable a more demanding and realistic test of photo-z methods. Using photometry from the Sloan Digital Sky Survey and spectroscopy from a collection of sources, we constructed data sets that mimic the biases between the underlying probability distribution of the real spectroscopic and photometric sample. We demonstrate the potential of these catalogues by submitting them to the scrutiny of different photo-z methods, including machine learning (ML) and template fitting approaches. Beyond the expected bad results from most ML algorithms for cases with missing coverage in the feature space, we were able to recognize the superiority of global models in the same situation and the general failure across all types of methods when incomplete coverage is convoluted with the presence of photometric errors - a data situation which photo-z methods were not trained to deal with up to now and which must be addressed by future large-scale surveys. Our catalogues represent the first controlled environment allowing a straightforward implementation of such tests.

AB - Two of the main problems encountered in the development and accurate validation of photometric redshift (photo-z) techniques are the lack of spectroscopic coverage in the feature space (e.g. colours and magnitudes) and the mismatch between the photometric error distributions associated with the spectroscopic and photometric samples. Although these issues are well known, there is currently no standard benchmark allowing a quantitative analysis of their impact on the final photo-z estimation. In this work, we present two galaxy catalogues, Teddy and Happy, built to enable a more demanding and realistic test of photo-z methods. Using photometry from the Sloan Digital Sky Survey and spectroscopy from a collection of sources, we constructed data sets that mimic the biases between the underlying probability distribution of the real spectroscopic and photometric sample. We demonstrate the potential of these catalogues by submitting them to the scrutiny of different photo-z methods, including machine learning (ML) and template fitting approaches. Beyond the expected bad results from most ML algorithms for cases with missing coverage in the feature space, we were able to recognize the superiority of global models in the same situation and the general failure across all types of methods when incomplete coverage is convoluted with the presence of photometric errors - a data situation which photo-z methods were not trained to deal with up to now and which must be addressed by future large-scale surveys. Our catalogues represent the first controlled environment allowing a straightforward implementation of such tests.

KW - Catalogues-galaxies

KW - Distances and redshifts

KW - Methods: data analysis

KW - Methods:statistical

KW - Techniques:photometric

UR - http://www.scopus.com/inward/record.url?scp=85016992727&partnerID=8YFLogxK

U2 - 10.1093/mnras/stx687

DO - 10.1093/mnras/stx687

M3 - Journal article

VL - 468

SP - 4323

EP - 4339

JO - Royal Astronomical Society. Monthly Notices

JF - Royal Astronomical Society. Monthly Notices

SN - 0035-8711

IS - 4

ER -