A Caltech Library Service

Identification of Single Spectral Lines through Supervised Machine Learning in a Large HST Survey (WISP): A Pilot Study for Euclid and WFIRST

Baronchelli, I. and Scarlata, C. M. and Rodighiero, G. and Rodríguez-Muñoz, L. and Bonato, M. and Bagley, M. and Henry, A. and Rafelski, M. and Malkan, M. and Colbert, J. and Dai, Y. S. and Dickinson, H. and Mancini, C. and Mehta, V. and Morselli, L. and Teplitz, H. I. (2020) Identification of Single Spectral Lines through Supervised Machine Learning in a Large HST Survey (WISP): A Pilot Study for Euclid and WFIRST. Astrophysical Journal Supplement Series, 249 (1). Art. No. 12. ISSN 1538-4365. doi:10.3847/1538-4365/ab9a3a.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Future surveys focusing on understanding the nature of dark energy (e.g., Euclid and WFIRST) will cover large fractions of the extragalactic sky in near-IR slitless spectroscopy. These surveys will detect a large number of galaxies that will have only one emission line in the covered spectral range. In order to maximize the scientific return of these missions, it is imperative that single emission lines are correctly identified. Using a supervised machine-learning approach, we classified a sample of single emission lines extracted from the WFC3 IR Spectroscopic Parallel survey, one of the closest existing analogs to future slitless surveys. Our automatic software integrates a spectral energy distribution (SED)-fitting strategy with additional independent sources of information. We calibrated it and tested it on a "gold" sample of securely identified objects with multiple lines detected. The algorithm correctly classifies real emission lines with an accuracy of 82.6%, whereas the accuracy of the SED-fitting technique alone is low (~50%) due to the limited amount of photometric data available (≤6 bands). While not specifically designed for the Euclid and WFIRST surveys, the algorithm represents an important precursor of similar algorithms to be used in these future missions.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Baronchelli, I.0000-0003-0556-2929
Scarlata, C. M.0000-0002-9136-8876
Rodighiero, G.0000-0002-9415-2296
Rodríguez-Muñoz, L.0000-0002-0192-5131
Bonato, M.0000-0001-9139-2342
Bagley, M.0000-0002-9921-9218
Henry, A.0000-0002-6586-4446
Rafelski, M.0000-0002-9946-4731
Malkan, M.0000-0001-6919-1237
Dai, Y. S.0000-0002-7928-416X
Dickinson, H.0000-0003-0475-008X
Mancini, C.0000-0002-4297-0561
Mehta, V.0000-0001-7166-6035
Teplitz, H. I.0000-0002-7064-5424
Additional Information:© 2020 The American Astronomical Society. Received 2019 November 28; revised 2020 May 25; accepted 2020 June 5; published 2020 July 13. I.B. thanks Alvio Renzini, Alberto Franceschini, Paolo Cassata, and Andrea Grazian for the useful discussion about the thematics discussed in the paper. C.S. acknowledges financial support from NASA, through STScI program number HST-AR-14311.001-A. STScI is operated by the Association of Universities for Research in Astronomy, Incorporated, under NASA contract NAS5-26555. M.B. acknowledges support from INAF under PRIN SKA/CTA FORECaST and from the Ministero degli Affari Esteri della Cooperazione Internazionale—Direzione Generale per la Promozione del Sistema Paese Progetto di Grande Rilevanza ZA18GR02. M.R. acknowledges financial support from NASA, through a grant from the Space Telescope Science Institute (STScI), program number HST-GO-14178.026-A.
Group:Infrared Processing and Analysis Center (IPAC)
Funding AgencyGrant Number
Istituto Nazionale di Astrofisica (INAF)UNSPECIFIED
Ministero degli affari esteri e della cooperazione internazionale (MAECI)ZA18GR02
Subject Keywords:Spectroscopy ; Algorithms ; Maximum likelihood estimation ; Spectral line identification ; Redshift surveys
Issue or Number:1
Classification Code:Unified Astronomy Thesaurus concepts: Spectroscopy (1558); Algorithms (1883); Maximum likelihood estimation (1901); Spectral line identification (2073); Redshift surveys (1378)
Record Number:CaltechAUTHORS:20200713-143726791
Persistent URL:
Official Citation:I. Baronchelli et al 2020 ApJS 249 12
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:104361
Deposited By: Tony Diaz
Deposited On:13 Jul 2020 21:55
Last Modified:16 Nov 2021 18:31

Repository Staff Only: item control page