The dataset used to select active galactic nucleus (AGN) candidates is labelled as G_all.csv. The two datasets selected by the two ensembles of neural controllers are labelled as G_0_ensemble.csv and G_all_ensemble.csv respectively. The dataset of detected AGN is labelled as agn.csv. In these four datasets, each source is described by the following columns:
ra (right ascension)
dec (declination)
z (photmetric redshift)
sfr (star-formation rate [log solar mass per year])
mass (stellar mass [log solar mass])
ks (Ks aperture magnitude)
The final four columns are the IRAC filters, with the values following the underscore indicating the band (in units of micrometer):
S_3.6
S_4.5
S_5.8
S_8.0
The values for these fields are extracted from the COSMOS2015 multiwavelength catalogue. A non-detection in any of the fields is indicated by the 'NA' keyword.
The .fits files for the four radiomaps are also attached: