Future surveys focusing on understanding the nature of dark energy (e.g., Euclid and WFIRST) will cover large fractions of the extragalactic sky in near-IR slitless spectroscopy. These surveys will detect a large number of galaxies that will have only one emission line in the covered spectral range. In order to maximize the scientific return of these missions, it is imperative that single emission lines are correctly identified. Using a supervised machine-learning approach, we classified a sample of single emission lines extracted from the WFC3 IR Spectroscopic Parallel survey, one of the closest existing analogs to future slitless surveys. Our automatic software integrates a spectral energy distribution (SED)-fitting strategy with additional independent sources of information. We calibrated it and tested it on a “gold” sample of securely identified objects with multiple lines detected. The algorithm correctly classifies real emission lines with an accuracy of 82.6%, whereas the...

中文翻译：

---

在大型HST调查（WISP）中通过监督机器学习识别单个光谱线：Euclid和WFIRST的先导研究

未来的研究重点是了解暗能量的性质（例如，欧几里得和WFIRST），将覆盖近红外无缝光谱学中大部分的银河外天空。这些调查将检测到在覆盖光谱范围内只有一条发射线的大量星系。为了使这些任务的科学回报最大化，必须正确识别单个发射线。使用监督的机器学习方法，我们对从WFC3红外光谱平行调查中提取的单个发射线样本进行了分类，这是与将来的无缝隙调查最接近的现有类似物之一。我们的自动软件将光谱能量分布（SED）拟合策略与其他独立的信息源集成在一起。我们对其进行了校准，并在“金”样的安全识别对象上进行了测试，并检测到多条线。该算法正确分类了真实的发射线，准确度为82.6％，而...