KiDSDR4 QSOs photometric redshifts catalog

We test three ML models: Random Forest (RF), XGBoost (XGB) and Artificial Neural Network (ANN). We find that XGB is the most robust and straightforward model for classification, while ANN performs the best for combined classification and redshift. The ANN inference results are tested using number counts, Gaia parallaxes and other quasar catalogs external to the training set.

Based on these tests, we derive the minimum classification probability for quasar candidates which provides the best purity vs. completeness trade-off: p(QSO_cand)>0.9 for r<22, and p(QSO_cand)>0.98 for 22<r<23.5. We find 158000 quasar candidates in the safe inference subset (r<22), and further 185000 in the reliable extrapolation regime (22<r<23.5). Test-data purity equals 97%, completeness is 94%, the latter dropping by 3% in the extrapolation to data fainter by one magnitude than the training set.

The photometric redshifts are derived with ANN and modeled with Gaussian uncertainties. Test-data redshift error (mean and scatter) equals 0.009+/-0.12 in the safe subset, and -0.0004+/-0.19 in the extrapolation, averaged over redshift range 0.14<z<3.63 (1st and 99th percentiles). Our success of the extrapolation challenges the way that models are optimized and applied at the faint data end.

The resulting catalog is ready for cosmology and Active Galactic Nucleus (AGN) studies.