arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.06607astro-ph.IM
收藏

基于卷积神经网络的SDSS图像测光红移

Photometric redshifts from SDSS images using a Convolutional Neural Network

Johanna Pasquet, Emmanuel Bertin, Marie Treyer, Stéphane Arnouts, Dominique Fouchez

摘要:

我们开发了一个深度卷积神经网络(CNN),用作分类器,以估计斯隆数字巡天的主要星系样本中z < 0.4的星系的光度红移和相关的概率分布函数(PDF)。我们的方法利用了图像中存在的所有信息,而无需任何特征提取。输入数据包括以光谱目标为中心的64x64像素的ugriz图像,加上视线上的银河系红化值。对于10万个或更多对象的训练集($\geq$占数据库的20%),我们达到了离散度$σ_{MAD}$ <0.01,显著低于从同一样本上的另一种机器学习技术获得的当前最佳离散度。偏差小于0.0001,与光度红移无关。PDF被证明具有非常好的预测能力。我们还发现,CNN的红移是无偏的星系倾斜,和$σ_{MAD}$降低与信噪比(SNR),达到低于0.007的SNR >100的值,如在条纹82的深堆叠区域。我们认为,对于大多数星系的精度是有限的SDSS图像的信噪比,而不是由该方法。这个实验在低红移下的成功为即将到来的调查开辟了有希望的前景。

英文摘要:

We developed a Deep Convolutional Neural Network (CNN), used as a classifier, to estimate photometric redshifts and associated probability distribution functions (PDF) for galaxies in the Main Galaxy Sample of the Sloan Digital Sky Survey at z < 0.4. Our method exploits all the information present in the images without any feature extraction. The input data consist of 64x64 pixel ugriz images centered on the spectroscopic targets, plus the galactic reddening value on the line-of-sight. For training sets of 100k objects or more ($\geq$ 20% of the database), we reach a dispersion $σ_{MAD}$<0.01, significantly lower than the current best one obtained from another machine learning technique on the same sample. The bias is lower than 0.0001, independent of photometric redshift. The PDFs are shown to have very good predictive power. We also find that the CNN redshifts are unbiased with respect to galaxy inclination, and that $σ_{MAD}$ decreases with the signal-to-noise ratio (SNR), achieving values below 0.007 for SNR >100, as in the deep stacked region of Stripe 82. We argue that for most galaxies the precision is limited by the SNR of SDSS images rather than by the method. The success of this experiment at low redshift opens promising perspectives for upcoming surveys.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑