Deep learning of multi-element abundances from high-resolution spectroscopic data
Deep learning of multi-element abundances from high-resolution spectroscopic data
复制标题
DOI：
10.1093/mnras/sty3217
复制
发表时间：
2018-08
影响因子：
4.8
通讯作者：
Henry W. Leung;J. Bovy
中科院分区：
文献类型：
--
作者：
Henry W. Leung;J. Bovy
人工神经网络的深度学习由于其在数据驱动天文学方面的潜力而越来越受到关注。然而，这种方法通常不提供不确定性，也不处理训练数据中的不完整性和噪声。在这项工作中，我们使用 APOGEE 数据设计了一个用于高分辨率光谱分析的神经网络，该数据模仿了标准光谱分析的方法：恒星参数是使用整个波长范围确定的，但单个元素丰度使用光谱的删失部分。我们使用定制的目标函数来训练该网络，该目标函数处理不完整和嘈杂的训练数据，并应用 dropout 变分推理来推导我们预测的不确定性。即使在低信噪比的情况下，我们也确定了 18 个单独元素在 $\大约 0.03$ dex 水平上的参数和丰度。我们证明，我们的方法返回的不确定性是对精度的实际估计，当遇到训练集之外的输入或输出时，它们会自动爆炸，从而保护用户免受不必要的外推。通过使用标准深度学习工具进行 GPU 加速，我们的方法速度非常快，可以在单个低成本 GPU 上在 10 分钟内分析整个 APOGEE 数据集的 $\approx250,000$ 光谱。我们发布了整个 APOGEE DR14 数据集的恒星参数和 18 个单个元素丰度以及相关的不确定性。同时，我们发布了 astroNN，这是一个为此工作开发的经过充分测试的开源 Python 包，但它也被设计为天文学深度学习的通用包。 astroNN 可通过此 https URL 获得，并在此 http URL 上提供大量文档。
Deep learning with artificial neural networks is increasingly gaining attention, because of its potential for data-driven astronomy. However, this methodology usually does not provide uncertainties and does not deal with incompleteness and noise in the training data. In this work, we design a neural network for high-resolution spectroscopic analysis using APOGEE data that mimics the methodology of standard spectroscopic analyses: stellar parameters are determined using the full wavelength range, but individual element abundances use censored portions of the spectrum. We train this network with a customized objective function that deals with incomplete and noisy training data and apply dropout variational inference to derive uncertainties on our predictions. We determine parameters and abundances for 18 individual elements at the $\approx 0.03$ dex level, even at low signal-to-noise ratio. We demonstrate that the uncertainties returned by our method are a realistic estimate of the precision and they automatically blow up when inputs or outputs outside of the training set are encountered, thus shielding users from unwanted extrapolation. By using standard deep-learning tools for GPU acceleration, our method is extremely fast, allowing analysis of the entire APOGEE data set of $\approx250,000$ spectra in ten minutes on a single, low-cost GPU. We release the stellar parameters and 18 individual-element abundances with associated uncertainty for the entire APOGEE DR14 dataset. Simultaneously, we release astroNN, a well-tested, open-source python package developed for this work, but that is also designed to be a general package for deep learning in astronomy. astroNN is available at this https URL with extensive documentation at this http URL.