论文标题
欧几里得准备：xxiii。使用模拟通量和H波段图像的深度机器学习的星系物理特性的推导
Euclid preparation: XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images
论文作者
论文摘要
下一代望远镜（例如Euclid，Rubin/LSST和Roman）将在宇宙上打开新窗口，从而使我们可以推断出数千万星系的物理特性。机器学习方法越来越成为处理大量数据的最有效工具，因为它们通常比传统方法更快，更准确。我们研究了如何通过深度学习算法来测量红移，恒星质量和恒星形成率（SFR），以模仿欧几里得和鲁宾/LSST调查的数据中观察到的星系。我们发现，依赖训练样本的参数空间的深度学习神经网络和卷积中性网络（CNN）在测量这些星系的性质方面表现良好，并且比基于光谱能量分布拟合的方法具有更好的精度。 CNN允许使用$ h _ {\ scriptScriptStryle \ rm e} $ - band Images一起处理多波段幅度。我们发现，恒星质量的估计值可以随着图像的使用而改善，但是红移和SFR的估计值却没有。我们最好的结果是i）在$ h _ {\ scriptScriptStryle \ rm e} $ -band中，带有s/n> 3的星系中的归一化误差小于0.15的红移; ii）恒星质量在两倍（$ \ sim0.3 \ rm dex $）的元素之内，该质量为99.5 $ \％$ $ \％$； iii）SFR以$ \ sim $ 70 $ \％$的样本的两个（$ \ sim0.3 \ rm dex $）的倍数（$ \ sim0.3 \ rm dex $）。我们讨论了我们的工作对调查应用的含义，以及如何通过深度学习来改善这些星系参数的测量。
Next generation telescopes, like Euclid, Rubin/LSST, and Roman, will open new windows on the Universe, allowing us to infer physical properties for tens of millions of galaxies. Machine learning methods are increasingly becoming the most efficient tools to handle this enormous amount of data, because they are often faster and more accurate than traditional methods. We investigate how well redshifts, stellar masses, and star-formation rates (SFR) can be measured with deep learning algorithms for observed galaxies within data mimicking the Euclid and Rubin/LSST surveys. We find that Deep Learning Neural Networks and Convolutional Neutral Networks (CNN), which are dependent on the parameter space of the training sample, perform well in measuring the properties of these galaxies and have a better accuracy than methods based on spectral energy distribution fitting. CNNs allow the processing of multi-band magnitudes together with $H_{\scriptscriptstyle\rm E}$-band images. We find that the estimates of stellar masses improve with the use of an image, but those of redshift and SFR do not. Our best results are deriving i) the redshift within a normalised error of less than 0.15 for 99.9$\%$ of the galaxies with S/N>3 in the $H_{\scriptscriptstyle\rm E}$-band; ii) the stellar mass within a factor of two ($\sim0.3 \rm dex$) for 99.5$\%$ of the considered galaxies; iii) the SFR within a factor of two ($\sim0.3 \rm dex$) for $\sim$70$\%$ of the sample. We discuss the implications of our work for application to surveys as well as how measurements of these galaxy parameters can be improved with deep learning.
