Large imaging surveys will rely on photometric redshifts (photo-z's), which are typically estimated through machine-learning methods. Currently planned spectroscopic surveys will not be deep enough to produce a representative training sample for Legacy Survey of Space and Time (LSST), so we seek methods to improve the photo-z estimates that arise from nonrepresentative training samples. Spectroscopic training samples for photo-z's are biased toward redder, brighter galaxies, which also tend to be at lower redshift than the typical galaxy observed by LSST, leading to poor photo-z estimates with outlier fractions nearly 4 times larger than for a representative training sample. In this Letter, we apply the concept of training sample augmentation, where we augment simulated nonrepresentative training samples with simulated galaxies possessing otherwise unrepresented features. When we select simulated galaxies with (g-z) color, i-band magnitude, and redshift outside the range of the original training sample, we are able to reduce the outlier fraction of the photo-z estimates for simulated LSST data by nearly 50% and the normalized median absolute deviation (NMAD) by 56%. When compared to a fully representative training sample, augmentation can recover nearly 70% of the degradation in the outlier fraction and 80% of the degradation in NMAD. Training sample augmentation is a simple and effective way to improve training samples for photo-z's without requiring additional spectroscopic samples.

中文翻译：

---

通过训练样本增强改进光度红移估计


大型成像调查将依赖于光度红移（photo-z），这通常是通过机器学习方法估计的。目前计划的光谱调查不够深入，无法为传统时空调查 (LSST) 生成代表性训练样本，因此我们寻求方法来改进非代表性训练样本中产生的 photo-z 估计。 photo-z 的光谱训练样本偏向于更红、更亮的星系，这些星系的红移也往往比 LSST 观测到的典型星系更低，导致 photo-z 估计值较差，异常值分数比代表性训练大近 4 倍样本。在这封信中，我们应用了训练样本增强的概念，即用具有其他未代表性特征的模拟星系来增强模拟的非代表性训练样本。当我们选择 (g-z) 颜色、i 波段星等和红移超出原始训练样本范围的模拟星系时，我们能够将模拟 LSST 数据的 photo-z 估计的异常值部分减少近 50%，标准化中位绝对偏差 (NMAD) 提高了 56%。与完全具有代表性的训练样本相比，增强可以恢复异常值部分中近 70% 的退化和 NMAD 中 80% 的退化。训练样本增强是一种简单而有效的方法，可以改进 photo-z 的训练样本，而无需额外的光谱样本。