We introduce QuasarNET, a deep convolutional neural network that performs
classification and redshift estimation of astrophysical spectra with
human-expert accuracy. We pose these two tasks as a \emph{feature detection}
problem: presence or absence of spectral features determines the class, and
their wavelength determines the redshift, very much like human-experts proceed.
When ran on BOSS data to identify quasars through their emission lines,
QuasarNET defines a sample $99.51\pm0.03$\% pure and $99.52\pm0.03$\% complete,
well above the requirements of many analyses using these data. QuasarNET
significantly reduces the problem of line-confusion that induces catastrophic
redshift failures to below 0.2\%. We also extend QuasarNET to classify spectra
with broad absorption line (BAL) features, achieving an accuracy of
$98.0\pm0.4$\% for recognizing BAL and $97.0\pm0.2$\% for rejecting non-BAL
quasars. QuasarNET is trained on data of low signal-to-noise and medium
resolution, typical of current and future astrophysical surveys, and could be
easily applied to classify spectra from current and upcoming surveys such as
eBOSS, DESI and 4MOST.

QuasarNET 是一款深度卷积神经网络，可分类和估算星系物理光谱的红移。该网络解决了光谱学的两个问题：存在或不存在波长决定样本，其频移程度则决定其红移，从而极大地减少了线的混淆和红移失败。

深度神经网络实现人类水平的光谱分类和红移测量

QuasarNET: Human-level spectral classification and redshifting with Deep  Neural Networks

Supernova (SN) classification and redshift estimation using photometric data
only have become very important for the Large Synoptic Survey Telescope (LSST),
given the large number of SNe that LSST will observe and the impossibility of
spectroscopically following up all the SNe. We investigate the performance of a
SN classifier that uses SN colors to classify LSST SNe with the Random Forest
classification algorithm. Our classifier results in an AUC of 0.98 which
represents excellent classification. We are able to obtain a photometric SN
sample containing 99$\%$ SNe Ia by choosing a probability threshold. We
estimate the photometric redshifts (photo-z) of SNe in our sample by fitting
the SN light curves using the SALT2 model with nested sampling. We obtain a
mean bias ($\left<z_\mathrm{phot}-z_\mathrm{spec}\right>$) of 0.012 with
$\sigma\left( \frac{z_\mathrm{phot}-z_\mathrm{spec}}{1+z_\mathrm{spec}}\right)
= 0.0294$ without using a host-galaxy photo-z prior, and a mean bias
($\left<z_\mathrm{phot}-z_\mathrm{spec}\right>$) of 0.0017 with $\sigma\left(
\frac{z_\mathrm{phot}-z_\mathrm{spec}}{1+z_\mathrm{spec}}\right) = 0.0116$
using a host-galaxy photo-z prior. Assuming a flat $\Lambda CDM$ model with
$\Omega_m=0.3$, we obtain $\Omega_m$ of $0.305\pm0.008$ (statistical errors
only), using the simulated LSST sample of photometric SNe Ia (with intrinsic
scatter $\sigma_\mathrm{int}=0.11$) derived using our methodology without using
host-galaxy photo-z prior. Our method will help boost the power of SNe from the
LSST as cosmological probes.

该研究使用 Random Forest 算法通过 SN 颜色对 LSST 中的 SNe 进行了分类和红移估计，并成功获得可靠的光度红移估计，从而证明该方法可用于提高 SNe 在宇宙学探针中的能力。