Deep learning methods for obtaining photometric redshift estimations from images
Deep learning methods for obtaining photometric redshift estimations from images
复制标题
从图像获取光度红移估计的深度学习方法
DOI：
10.1093/mnras/stac480
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
Henghes B
中科院分区：
文献类型：
--
作者：
Henghes B
了解星系的红移是许多宇宙学实验的首要要求之一，由于不可能对观察到的每个星系进行光谱分析，光度红移（photo-z）估计仍然是特别有趣的。在这里，我们研究了直接从图像中获得照片估计的不同深度学习方法，并将这些方法与“传统”机器学习算法进行了比较，这些算法利用通过光度法检索的星等。除了测试卷积神经网络（CNN）和初始模块CNN外，我们还引入了一种新的混合输入模型，该模型允许在同一模型中使用图像和星等数据，作为进一步改进估计红移的一种方式。我们还执行基准测试，作为演示不同算法的性能和可伸缩性的一种方式。研究中使用的数据完全来自斯隆数字巡天（SDSS），其中使用了100万个星系，每个星系都有5滤镜（ugriz）图像，具有完整的光度测定和光谱红移，这被视为基本事实。混合输入初始CNN的均方误差(MSE) =0.009，比传统随机森林（RF）有了显著的改进（），在z< 0.3的范围内，该模型在较低的红移下表现更好，实现了aMSE= 0.0007（比RF有所改善）。这种方法可能对即将到来的调查非常有益，比如欧几里得和维拉·c·鲁宾天文台的时空遗留调查（LSST），这将需要尽可能快速准确地产生大量的照片估计。
Knowing the redshift of galaxies is one of the first requirements of many cosmological experiments, and as it is impossible to perform spectroscopy for every galaxy being observed, photometric redshift (photo-z) estimations are still of particular interest. Here, we investigate different deep learning methods for obtaining photo-zestimates directly from images, comparing these with ‘traditional’ machine learning algorithms which make use of magnitudes retrieved through photometry. As well as testing a convolutional neural network (CNN) and inception-module CNN, we introduce a novel mixed-input model that allows for both images and magnitude data to be used in the same model as a way of further improving the estimated redshifts. We also perform benchmarking as a way of demonstrating the performance and scalability of the different algorithms. The data used in the study comes entirely from the Sloan Digital Sky Survey (SDSS) from which 1 million galaxies were used, each having 5-filtre (ugriz) images with complete photometry and a spectroscopic redshift which was taken as the ground truth. The mixed-input inception CNN achieved a mean squared error (MSE) =0.009, which was a significant improvement () over the traditional random forest (RF), and the model performed even better at lower redshifts achieving aMSE= 0.0007 (aimprovement over the RF) in the range ofz< 0.3. This method could be hugely beneficial to upcoming surveys, such as Euclid and the Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST), which will require vast numbers of photo-zestimates produced as quickly and accurately as possible.