Cataloging Accreted Stars within Gaia DR2 Using Deep Learning

In [1907.06652], a neural network is used to determine whether a star was accreted onto the Milky Way or was born in situ using only 5D phase space information. The inputs to the network are [l, b, parallax, pmra, pmdec] from the Gaia DR2 catalog. Stars with a score greater than 0.75 are marked as accreted. The subset of stars with 6D phase space information was studied in more detail in [1907.07190] and [1907.07681].

In this release of the catalog, the data is in the HDF5 file format. We recommended using the pandas package within python (with pytables installed). Then the DataFrame can be loaded with 

Stars = pd.read_hdf('Public_AllStars_6D.h5')

We have included 4 different files. The scores for all of the stars with \(\delta \varpi / \varpi < 0.1\) are given in Public_AllStars_5D.h5. The subset of these stars which also have line-of-sight velocity measurements are given in Public_AllStars_6D.h5. The files denoted with SelectedByNetwork have only stars which pass the neural network selection as being accreted, with 5D and 6D the same as for AllStars. Each file include the columns

source_id, int64

l, float64

b, float64

ra, float64

dec, float64

parallax, float64

pmra, float64

pmdec, float64

phot_g_mean_mag, float32

phot_bp_mean_mag, float32

phot_rp_mean_mag, float32

radial_velocity, float64

Score, float32

PhotometricScores, float32

The "source_id" should match with Gaia DR2, allowing for easy cross referencing. The "Score" column is the output of the network using only 5D kinematic information, to be considered as accreted, the score needs to be larger than 0.75. The "PhotometricScores" column is the network output for the neural network which uses the "phot" columns along with the 5D kinematics. The optimal cut for this is 0.9, but as shown in the paper, these results are less robust than the first network.

If you use our catalog in any of your works, please cite 
@article{Ostdiek:2019gnb,
     author         = "Ostdiek, Bryan and Necib, Lina and Cohen, Timothy and
                       Freytsis, Marat and Lisanti, Mariangela and
                       Garrison-Kimmel, Shea and Wetzel, Andrew and Sanderson,
                       Robyn E. and Hopkins, Philip F.",
     title          = "{Cataloging Accreted Stars within Gaia DR2 using Deep
                       Learning}",
     year           = "2019",
     eprint         = "1907.06652",
     archivePrefix  = "arXiv",
     primaryClass   = "astro-ph.GA",
     SLACcitation   = "%%CITATION = ARXIV:1907.06652;%%”
}
and 
@article{Necib:2019zka,
     author         = "Necib, Lina and Ostdiek, Bryan and Lisanti, Mariangela
                       and Cohen, Timothy and Freytsis, Marat and
                       Garrison-Kimmel, Shea",
     title          = "{Chasing Accreted Structures within Gaia DR2 using Deep
                       Learning}",
     year           = "2019",
     eprint         = "1907.07681",
     archivePrefix  = "arXiv",
     primaryClass   = "astro-ph.GA",
     SLACcitation   = "%%CITATION = ARXIV:1907.07681;%%”
}.
Also, please cite 
@article{Necib:2019zbk,
     author         = "Necib, Lina and Ostdiek, Bryan and Lisanti, Mariangela
                       and Cohen, Timothy and Freytsis, Marat and
                       Garrison-Kimmel, Shea and Hopkins, Philip F. and Wetzel,
                       Andrew and Sanderson, Robyn",
     title          = "{Evidence for a Vast Prograde Stellar Stream in the Solar
                       Vicinity}",
     year           = "2019",
     eprint         = "1907.07190",
     archivePrefix  = "arXiv",
     primaryClass   = "astro-ph.GA",
     SLACcitation   = "%%CITATION = ARXIV:1907.07190;%%"
}
for any follow up study of Nyx.