A machine learning approach to galaxy properties: Joint redshift-stellar mass probability distributions with Random Forest

Autor: A. A. Plazas, L. N. Da Costa, W. G. Hartley, Maria E. S. Pereira, Brian Yanny, Marcos Lima, Alex Drlica-Wagner, J. Carretero, Antonella Palmese, E. M. Huff, Juan Garcia-Bellido, Ramon Miquel, M. A. G. Maia, Michel Aguena, V. Scarpine, A. Choi, Martin Crocce, F. J. Castander, G. Tarle, R. D. Wilkinson, Ian Harrison, S. Mucesh, K. Honscheid, Sunayana Bhargava, A. Alarcon, J. De Vicente, David J. James, Huan Lin, Pablo Fosalba, M. Carrasco Kind, Chun-Hao To, Alexandra Amon, E. J. Sanchez, F. Paz-Chinchón, Keith Bechtol, E. Suchyta, August E. Evrard, M. Costanzi, M. Smith, Felipe Menanteau, Josh Frieman, D. L. Hollowood, S. Allam, Robert A. Gruendl, S. Serrano, Ofer Lahav, Daniel Gruen, Samuel Hinton, Peter Melchior, Christopher J. Conselice, Erin Sheldon, B. Flaugher, E. Bertin, G. Gutierrez, David J. Brooks, S. Desai, Enrique Gaztanaga, Robert Morgan, J. Gschwend, S. Everett, D. W. Gerdes, Gary Bernstein, I. Ferrero, H. T. Diehl, David Bacon, I. Sevilla-Noarbe, N. Kuropatkin, K. D. Eckert, T. N. Varga, Asa F. L. Bluck, Kyler Kuehn, Michael Schubnell, Daniel Thomas, L. Whiteway, A. Carnero Rosell
Přispěvatelé: National Science Foundation (US), Ministerio de Ciencia, Innovación y Universidades (España), Generalitat de Catalunya, European Commission, Instituto Nacional de Ciência e Tecnologia (Brasil), Institut d'Astrophysique de Paris (IAP), Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), DES, Mucesh, S., Hartley, W. G., Palmese, A., Lahav, O., Whiteway, L., Amon, A., Bechtol, K., Bernstein, G. M., Carnero Rosell, A., Carrasco Kind, M., Choi, A., Eckert, K., Everett, S., Gruen, D., Gruendl, R. A., Harrison, I., Huff, E. M., Kuropatkin, N., Sevilla-Noarbe, I., Sheldon, E., Yanny, B., Aguena, M., Allam, S., Bacon, D., Bertin, E., Bhargava, S., Brooks, D., Carretero, J., Castander, F. J., Conselice, C., Costanzi, M., Crocce, M., da Costa, L. N., Pereira, M. E. S., De Vicente, J., Desai, S., Diehl, H. T., Drlica-Wagner, A., Evrard, A. E., Ferrero, I., Flaugher, B., Fosalba, P., Frieman, J., García-Bellido, J., Gaztanaga, E., Gerdes, D. W., Gschwend, J., Gutierrez, G., Hinton, S. R., Hollowood, D. L., Honscheid, K., James, D. J., Kuehn, K., Lima, M., Lin, H., Maia, M. A. G., Melchior, P., Menanteau, F., Miquel, R., Morgan, R., Paz-Chinchón, F., Plazas, A. A., Sanchez, E., Scarpine, V., Schubnell, M., Serrano, S., Smith, M., Suchyta, E., Tarle, G., Thomas, D., To, C., Varga, T. N., Wilkinson, R. D.
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
statistical [Methods]
software: data analysis
computer.software_genre
01 natural sciences
data analysi [software]
Copula (probability theory)
Machine Learning (cs.LG)
Astrophysics - Cosmology and Nongalactic Astrophysic
data analysis [Methods]
010303 astronomy & astrophysics
Physics
fundamental parameter [galaxies]
galaxies: fundamental parameters
Random forest
Software: public realese
fundamental parameters [Galaxies]
Probability distribution
galaxies: evolution
Astrophysics - Instrumentation and Methods for Astrophysics
Astrophysics - Cosmology and Nongalactic Astrophysics
public realese [Software]
Cosmology and Nongalactic Astrophysics (astro-ph.CO)
methods: data analysis
methods: statistical
software: public release
Astrophysics - Astrophysics of Galaxies
FOS: Physical sciences
Astrophysics::Cosmology and Extragalactic Astrophysics
Machine learning
Astrophysics - Astrophysics of Galaxie
0103 physical sciences
Galaxy formation and evolution
[INFO]Computer Science [cs]
[PHYS.PHYS.PHYS-INS-DET]Physics [physics]/Physics [physics]/Instrumentation and Detectors [physics.ins-det]
Probability integral transform
Instrumentation and Methods for Astrophysics (astro-ph.IM)
010308 nuclear & particles physics
business.industry
Univariate
Astronomy and Astrophysics
evolution [Galaxies]
public release [software]
Redshift
Galaxy
Space and Planetary Science
data analysis [Software]
Astrophysics of Galaxies (astro-ph.GA)
data analysi [methods]
Artificial intelligence
Astrophysics - Instrumentation and Methods for Astrophysic
[PHYS.ASTR]Physics [physics]/Astrophysics [astro-ph]
business
computer
Zdroj: Digital.CSIC. Repositorio Institucional del CSIC
instname
Mon.Not.Roy.Astron.Soc.
Mon.Not.Roy.Astron.Soc., 2021, 502 (2), pp.2770-2786. ⟨10.1093/mnras/stab164⟩
ISSN: 0035-8711
Popis: We demonstrate that highly accurate joint redshift-stellar mass probability distribution functions (PDFs) can be obtained using the Random Forest (RF) machine learning (ML) algorithm, even with few photometric bands available. As an example, we use the Dark Energy Survey (DES), combined with the COSMOS2015 catalogue for redshifts and stellar masses. We build two ML models: one containing deep photometry in the $griz$ bands, and the second reflecting the photometric scatter present in the main DES survey, with carefully constructed representative training data in each case. We validate our joint PDFs for $10,699$ test galaxies by utilizing the copula probability integral transform and the Kendall distribution function, and their univariate counterparts to validate the marginals. Benchmarked against a basic set-up of the template-fitting code BAGPIPES, our ML-based method outperforms template fitting on all of our predefined performance metrics. In addition to accuracy, the RF is extremely fast, able to compute joint PDFs for a million galaxies in just under $6$ min with consumer computer hardware. Such speed enables PDFs to be derived in real time within analysis codes, solving potential storage issues. As part of this work we have developed GALPRO, a highly intuitive and efficient Python package to rapidly generate multivariate PDFs on-the-fly. GALPRO is documented and available for researchers to use in their cosmology and galaxy evolution studies.
Comment: 18 pages, 8 figures, Accepted by MNRAS
Databáze: OpenAIRE
Externí odkaz: