We present a method of selecting quasars up to redshift ≈6 with random forests, a supervised machine-learning method, applied to Pan-STARRS1 and WISE data. We find that, thanks to the increasing set of known quasars, we can assemble a training set that enables supervised machine-learning algorithms to become a competitive alternative to other methods up to this redshift. We present a candidate set for the redshift range 4.8–6.3, which includes the region around z=5.5 where selecting quasars is difficult due to their photometric similarity to red and brown dwarfs. We demonstrate that, under our survey restrictions, we can reach a high completeness (66%7% below redshift 5.6/ above redshift 5.6) while maintaining a high selection efficiency (/). Our selection efficiency is estimated via a novel method based on the different distributions of quasars and contaminants on the sky. The final catalog of 515 candidates includes 225 known quasars. We predict the candidate catalog to contain additional new quasars below redshift 5.6 and above, and we make the catalog publicly available. Spectroscopic follow-up observations of 37 candidates led us to discover 20 new high redshift quasars (18 at 4.6≤z≤5.5, 2 z∼5.7). These observations are consistent with our predictions on efficiency. We argue that random forests can lead to higher completeness because our candidate set contains a number of objects that would be rejected by common color cuts, including one of the newly discovered redshift 5.7 quasars.

我们提出了一种使用随机森林选择红移 ≈6 类星体的方法，这是一种适用于 Pan-STARRS1 和 WISE 数据的监督机器学习方法。我们发现，由于已知类星体的数量不断增加，我们可以组装一个训练集，使受监督的机器学习算法成为在此红移之前的其他方法的竞争替代品。我们提出了红移范围 4.8-6.3 的候选集，其中包括z = 5.5附近的区域，由于类星体与红矮星和棕矮星的光度相似，因此难以选择类星体。我们证明，在我们的调查限制下，我们可以在保持高选择效率（/）。我们的选择效率是通过一种基于类星体和污染物在天空中的不同分布的新方法来估计的。515 个候选者的最终目录包括 225 个已知类星体。我们预测候选目录包含红移 5.6 及以上的其他新类星体，并且我们公开目录。37名考生光谱随访观察使我们发现20个新高红移类星体（18日4.6≤ ž ≤5.5，2 ž ~5.7）。这些观察结果与我们对效率的预测一致。我们认为随机森林可以导致更高的完整性，因为我们的候选集包含许多会被常见颜色切割拒绝的对象，包括新发现的红移 5.7 类星体之一。