Abstract A comprehensive and high-purity quasar candidate catalogue with precise redshift measurements is crucial for advancing quasar research and cosmology. In the era of extensive sky surveys, the efficient identification of quasars from large-scale datasets has become a significant challenge in modern astronomy. By cross-matching the J-PLUS DR3 dataset with unWISE and numerous spectroscopic datasets with accurate classifications, we compiled a known sample of 740 562 sources, including 338 456 stars, 320 606 galaxies, and 81 500 quasars. Subsequently, we developed several classification models employing XGBoost, CatBoost, and deep learning techniques. Through optimization of feature selection and hyperparameter tuning for each model, we derived an optimal classification model. This model achieved an accuracy of 99 per cent, with the Precision and Recall for quasar detection reaching 98.20 per cent and 99.39 per cent, respectively. In parallel, we utilized the known quasar sample to train an optimal model for redshift estimation, achieving a mean squared error (MSE) of 0.139. Finally, combining the optimal classification and regression models, we designed an efficient workflow for quasar candidate selection and redshift estimation. This process resulted in the identification of over 3 million quasar candidates with photometric redshifts from the J-PLUS DR3 dataset. These candidates provide an invaluable input catalogue for subsequent observations by large-scale spectroscopic surveys, such as LAMOST, SDSS, DESI, or other ongoing efforts in this field.
Yang et al. (Thu,) studied this question.