ArborZ: PHOTOMETRIC REDSHIFTS USING BOOSTED DECISION TREES

被引：96

作者：

Gerdes, David W. ^{[1
]}

Sypniewski, Adam J. ^{[1
]}

McKay, Timothy A. ^{[1
]}

Hao, Jiangang ^{[1
]}

Weis, Matthew R. ^{[1
]}

Wechsler, Risa H. ^{[2
,3
]}

Busha, Michael T. ^{[2
,3
]}

机构：

[1] Univ Michigan, Dept Phys, Ann Arbor, MI 48109 USA

[2] Stanford Univ, Kavli Inst Particle Phys Astrophys & Cosmol, Dept Phys, Stanford, CA 94305 USA

[3] Stanford Univ, SLAC Natl Lab, Stanford, CA 94305 USA

来源：

ASTROPHYSICAL JOURNAL | 2010年 / 715卷 / 02期

基金：

美国国家航空航天局; 美国国家科学基金会;

关键词：

galaxies: distances and redshifts; galaxies: statistics; large-scale structure of universe; methods: data analysis; methods: statistical; DIGITAL SKY SURVEY; SPECTROSCOPIC TARGET SELECTION; DEEP; SDSS; MACHINE; MASS; LUMINOSITY; EVOLUTION; GALAXIES; QUASARS;

D O I：

10.1088/0004-637X/715/2/823

中图分类号：

P1 [天文学];

学科分类号：

0704 ;

摘要：

Precision photometric redshifts will be essential for extracting cosmological parameters from the next generation of wide-area imaging surveys. In this paper, we introduce a photometric redshift algorithm, ArborZ, based on the machine-learning technique of boosted decision trees. We study the algorithm using galaxies from the Sloan Digital Sky Survey (SDSS) and from mock catalogs intended to simulate both the SDSS and the upcoming Dark Energy Survey. We show that it improves upon the performance of existing algorithms. Moreover, the method naturally leads to the reconstruction of a full probability density function (PDF) for the photometric redshift of each galaxy, not merely a single "best estimate" and error, and also provides a photo-z quality figure of merit for each galaxy that can be used to reject outliers. We show that the stacked PDFs yield a more accurate reconstruction of the redshift distribution N(z). We discuss limitations of the current algorithm and ideas for future work.

引用

页码：823 / 832

页数：10

共 50 条

[1] Ventriculogram segmentation using boosted decision trees.
McDonald, JA
Sheehan, FH
[J]. MEDICAL IMAGING 2004: IMAGE PROCESSING, PTS 1-3, 2004, 5370 : 1804 - 1814
[2] Reweighting with Boosted Decision Trees
Rogozhnikov, Alex
[J]. 17TH INTERNATIONAL WORKSHOP ON ADVANCED COMPUTING AND ANALYSIS TECHNIQUES IN PHYSICS RESEARCH (ACAT2016), 2016, 762
[3] Boosted Decision Trees and Applications
Coadou, Yann
[J]. SOS 2012 - IN2P3 SCHOOL OF STATISTICS, 2013, 55
[4] Improving Photometric Redshifts Using Different Photometric Parameters
Wang, Tao
Cu, Q. -S.
Huang, J. -S.
[J]. STARBURST-AGN CONNECTION, 2009, 408 : 215 - +
[5] Improving Supreme Court Forecasting Using Boosted Decision Trees
Kaufman, Aaron Russell
Kraft, Peter
Sen, Maya
[J]. POLITICAL ANALYSIS, 2019, 27 (03) : 381 - 387
[6] Predicting the outcome of construction litigation using boosted decision trees
Arditi, D
Pulket, T
[J]. JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2005, 19 (04) : 387 - 393
[7] Supervised Hashing Using Graph Cuts and Boosted Decision Trees
Lin, Guosheng
Shen, Chunhua
van den Hengel, Anton
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (11) : 2317 - 2331
[8] Galaxy clustering using photometric redshifts
Soltan, A. M.
Chodorowski, M. J.
[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2015, 453 (01) : 1013 - 1025
[9] Photometric redshifts using submm wavelengths
Wiklind, T
[J]. ASTRONOMY, COSMOLOGY AND FUNDAMENTAL PHYSICS, PROCEEDINGS, 2003, : 491 - 492
[10] Measuring the Probabilistic Photometric Redshifts of X-ray Quasars Based on the Quantile Regression of Ensembles of Decision Trees
Meshcheryakov, A. V.
Glazkova, V. V.
Gerasimov, S. V.
Mashechkin, I. V.
[J]. ASTRONOMY LETTERS-A JOURNAL OF ASTRONOMY AND SPACE ASTROPHYSICS, 2018, 44 (12): : 735 - 753

← 1 2 3 4 5 →