J/other/RAA/22.F5014 New lens candidates from GaSNets (Zhong+, 2022)
Galaxy Spectra Neural Networks (GaSNets).
I. Searching for Strong Lens Candidates in eBOSS Spectra Using Deep Learning.
Zhong F., Li R., Napolitano N.R.
<Res. Astron. Astrophys., 22, 065014 (2022)>
=2022RAA....22f5014Z 2022RAA....22f5014Z (SIMBAD/NED BibCode)
ADC_Keywords: Gravitational lensing ; Redshifts ; Optical
Abstract:
With the advent of new spectroscopic surveys from ground and space,
observing up to hundreds of millions of galaxies, spectra
classification will become overwhelming for standard analysis
techniques. To prepare for this challenge, we introduce a family of
deep learning tools to classify features in one-dimensional spectra.
As the first application of these Galaxy Spectra neural Networks
(GaSNets), we focus on tools specialized in identifying emission lines
from strongly lensed star-forming galaxies in the eBOSS spectra. We
first discuss the training and testing of these networks and define a
threshold probability, PL, of 95% for the high-quality event
detection. Then, using a previous set of spectroscopically selected
strong lenses from eBOSS, confirmed with the Hubble Space Telescope
(HST), we estimate a completeness of ∼80% as the fraction of lenses
recovered above the adopted PL. We finally apply the GaSNets to
∼1.3M eBOSS spectra to collect the first list of ∼430 new
high-quality candidates identified with deep learning from
spectroscopy and visually graded as highly probable real events. A
preliminary check against ground-based observations tentatively shows
that this sample has a confirmation rate of 38%, in line with previous
samples selected with standard (no deep learning) classification tools
and confirmed by the HST. This first test shows that machine learning
can be efficiently extended to feature recognition in the wavelength
space, which will be crucial for future surveys like 4MOST, DESI,
Euclid, and the China Space Station Telescope.
Description:
The new algorithm is made of different CNNs, dubbed Galaxy Spectra
convolutional neural Networks (GaSNets). These are optimized to work
together to provide SGL candidates, but can also perform
classification and regression tasks independently. As such, they are
extremely suitable for further applications in large databases of tens
to hundreds of millions of spectra, like the ones expected from the
next generation spectroscopic surveys (4MOST, DESI, EUCLID, CSST).
In this paper, we have started by applying these new tools to the
strong lensing search in the eBOSS/DR16 database (Ahumada et al.,
2020ApJS..249....3A 2020ApJS..249....3A, Cat. V/154). To this aim we have introduced: (1)
GaSNet-L1 giving to each eBOSS spectrum the probability to be an SGL
event (PL); (2) GaSNet-L2 estimating the redshift of background
sources (zPE) from a series of pre-selected emission lines and (3)
GaSNet-L3 estimating the redshift of the galaxy itself (zPG), using
the information it learns from the continuous spectrum, including
local absorption/emission features.
We have collected ∼930 candidates that have been further cleaned by
misclassified SGL events, via visual inspection. The final sample of
visual HQ candidates is made of 497 spectroscopic selected objects.
This catalog has been a posteriori compared to the most extended
catalog of spectroscopic selected lens candidates from Talbot et al.
(2021MNRAS.502.4617T 2021MNRAS.502.4617T) and found an overlap of only 68 candidates,
meaning that 429 of our candidates are newly found.
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
appena.dat 71 429 New high quality (HQ) candidates from GaSNets
--------------------------------------------------------------------------------
See also:
V/154 : Sloan Digital Sky Surveys (SDSS), Release 16 (DR16) (Ahumada+, 2020)
Byte-by-byte Description of file: appena.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 3 I3 --- Seq Sequential number
5- 12 F8.4 deg RAdeg Right ascension (J2000)
14- 20 F7.4 deg DEdeg Declination (J2000)
22- 26 I5 --- Plate Plate identifier
28- 32 I5 --- MJD MJD identifier
34- 36 I3 --- Fiber Fiber identifier
38- 42 F5.3 --- PL GaSNet-L1 probability
44- 48 F5.3 --- z Redshift of the galaxy from the eBOSS catalog
50- 54 F5.3 --- zPG Predicted redshift of the galaxy
from GaSNet-L3
56- 60 F5.3 --- zPE Predicted redshift of the background source
from GaSNet-L2
62- 66 F5.3 --- meaneyeZE Corrected redshift of the source
from the visual inspection
68- 71 F4.2 --- PT Total probability, PT=PLx0.1 visual scores,
i.e., combining the GaSNets and human
probabilities to be a lens
--------------------------------------------------------------------------------
History:
From electronic version of the journal
(End) Patricia Vannier [CDS] 20-Jun-2023