ZTF DR11 classification in ZTF/4MOST sky

We used a hierarchical local classifier per parent node approach, where each node was composed of a balanced random forest model. We adopted a 17-class taxonomy, including non-variable stars and galaxies, three transients (SNIa, SN-other, and CV/Nova), five classes of stochastic variables (lowz-AGN, midz-AGN, highz-AGN, Blazar, and YSO), and seven classes of periodic variables (LPV, EA, EB/EW, DSCT, RRL, CEP, and Periodic-other).

The macro averaged precision, recall and F1-score are 0.61, 0.75, and 0.62 for the g-band model, and 0.60, 0.74, and 0.61, for the r-band model. When grouping the four AGN classes (lowz-AGN, midz-AGN, highz-AGN, and Blazar) into one single class, its precision, recall, and F1-score are 1.00, 0.95, and 0.97, respectively, for both the $g$ and r bands. This demonstrates the good performance of the model classifying AGN candidates.

We applied the model to all the sources in the ZTF/4MOST overlapping sky (-28<=DE<=8.5), avoiding ZTF fields covering the Galactic bulge (|gal_b_|<=9 and gal_l_<=50). This area includes 86576577 light curves in the g-band and 140409824 in the r-band, with 20 or more observations, and with an average magnitude in the corresponding band lower than 20.5. Only 0.73% of the $g$-band light curves and 2.62% of the $r$-band light curves were classified as stochastic, periodic, or transient with high probability (P_init_>=0.9).

Even though the metrics obtained for both models are similar, we found that, in general, more reliable results are obtained when using the g-band model. Using the latter, we identified 384242 AGN candidates (including low-, mid-, and high-redshift AGNs and Blazars), 287156 of which have P_init_>=0.9.