DESI is a groundbreaking international project to observe more than 40
million quasars and galaxies over a 5-year period to create a 3D map of the
sky. This map will enable us to probe multiple aspects of cosmology, from dark
energy to neutrino mass. We are focusing here on one type of object observed by
DESI, the Lyman Break Galaxies (LBGs). The aim is to use their spectra to
determine whether they are indeed LBGs, and if so, to determine their distance
from the Earth using a phenomenon called redshift. This will enable us to place
these galaxies on the DESI 3D map.
The aim is therefore to develop a convolutional neural network (CNN) inspired
by QuasarNET (See arXiv:1808.09955), performing simultaneously a classification
(LBG type or not) and a regression task (determine the redshift of the LBGs).
Initially, data augmentation techniques such as shifting the spectra in
wavelengths, adding noise to the spectra, or adding synthetic spectra were used
to increase the model training dataset from 3,019 data to over 66,000. In a
second phase, modifications to the QuasarNET architecture, notably through
transfer learning and hyperparameter tuning with Bayesian optimization, boosted
model performance.
Gains of up to 26% were achieved on the Purity/Efficiency curve, which is
used to evaluate model performance, particularly in areas with interesting
redshifts, at low (around 2) and high (around 4) redshifts. The best model
obtained an average score of 94%, compared with 75% for the initial model.

利用基于卷积神经网络 (CNN) 的 QuasarNET 模型和数据增强技术，本研究通过确定 Laman Break Galaxies (LBGs) 是否是 LBGs 以及通过红移确定它们与地球的距离，进而将这些星系放置在 DESI 的 3D 地图上，提高模型性能并实现了高达 94% 的平均得分。

基于卷积神经网络的 Lyman 断层星系分类与 DESI 中红移回归

Convolutional neural network for Lyman break galaxies classification and  redshift regression in DESI (Dark Energy Spectroscopic Instrument)

We use angular clustering of luminous red galaxies from the Dark Energy
Spectroscopic Instrument (DESI) imaging surveys to constrain the local
primordial non-Gaussianity parameter fNL. Our sample comprises over 12 million
targets, covering 14,000 square degrees of the sky, with redshifts in the range
0.2< z < 1.35. We identify Galactic extinction, survey depth, and astronomical
seeing as the primary sources of systematic error, and employ linear regression
and artificial neural networks to alleviate non-cosmological excess clustering
on large scales. Our methods are tested against log-normal simulations with and
without fNL and systematics, showing superior performance of the neural network
treatment in reducing remaining systematics. Assuming the universality
relation, we find fNL $= 47^{+14(+29)}_{-11(-22)}$ at 68\%(95\%) confidence.
With a more aggressive treatment, including regression against the full set of
imaging maps, our maximum likelihood value shifts slightly to fNL$ \sim 50$ and
the uncertainty on fNL increases due to the removal of large-scale clustering
information. We apply a series of robustness tests (e.g., cuts on imaging,
declination, or scales used) that show consistency in the obtained constraints.
Despite extensive efforts to mitigate systematics, our measurements indicate
fNL > 0 with a 99.9 percent confidence level. This outcome raises concerns as
it could be attributed to unforeseen systematics, including calibration errors
or uncertainties associated with low-\ell systematics in the extinction
template. Alternatively, it could suggest a scale-dependent fNL model--causing
significant non-Gaussianity around large-scale structure while leaving cosmic
microwave background scales unaffected. Our results encourage further studies
of fNL with DESI spectroscopic samples, where the inclusion of 3D clustering
modes should help separate imaging systematics.

使用 DESI 个人计划中红巨星星系的角聚类方法，探讨局部原初非高斯性参数 fNL；结果表明 fNL>0 且具有 99.9％的置信水平，呼吁进一步研究带有 3D 聚类的 DESI 光谱样品以确保提取成像系统漂移。

来自光度 DESI 亮红星系的大尺度聚类的本地原始非高斯性

Local primordial non-Gaussianity from the large-scale clustering of  photometric DESI luminous red galaxies

DESI (Dark Energy Spectroscopic Instrument) is a Stage IV ground-based dark
energy experiment that will study baryon acoustic oscillations (BAO) and the
growth of structure through redshift-space distortions with a wide-area galaxy
and quasar redshift survey. To trace the underlying dark matter distribution,
spectroscopic targets will be selected in four classes from imaging data. We
will measure luminous red galaxies up to $z=1.0$. To probe the Universe out to
even higher redshift, DESI will target bright [O II] emission line galaxies up
to $z=1.7$. Quasars will be targeted both as direct tracers of the underlying
dark matter distribution and, at higher redshifts ($ 2.1 < z < 3.5$), for the
Ly-$\alpha$ forest absorption features in their spectra, which will be used to
trace the distribution of neutral hydrogen. When moonlight prevents efficient
observations of the faint targets of the baseline survey, DESI will conduct a
magnitude-limited Bright Galaxy Survey comprising approximately 10 million
galaxies with a median $z\approx 0.2$. In total, more than 30 million galaxy
and quasar redshifts will be obtained to measure the BAO feature and determine
the matter power spectrum, including redshift space distortions.

DESI （暗能量光谱仪）是一项地基暗能量实验，将通过广阔的星系和类星体红移巡测研究声学波动和红移空间畸变的结构增长，以追踪基础暗物质的分布。

DESI 实验第一部分：科学，目标和调查设计

The DESI Experiment Part I: Science,Targeting, and Survey Design

DESI (Dark Energy Spectropic Instrument) is a Stage IV ground-based dark
energy experiment that will study baryon acoustic oscillations and the growth
of structure through redshift-space distortions with a wide-area galaxy and
quasar redshift survey. The DESI instrument is a robotically-actuated,
fiber-fed spectrograph capable of taking up to 5,000 simultaneous spectra over
a wavelength range from 360 nm to 980 nm. The fibers feed ten three-arm
spectrographs with resolution $R= \lambda/\Delta\lambda$ between 2000 and 5500,
depending on wavelength. The DESI instrument will be used to conduct a
five-year survey designed to cover 14,000 deg$^2$. This powerful instrument
will be installed at prime focus on the 4-m Mayall telescope in Kitt Peak,
Arizona, along with a new optical corrector, which will provide a three-degree
diameter field of view. The DESI collaboration will also deliver a
spectroscopic pipeline and data management system to reduce and archive all
data for eventual public use.

DESI 是一种大面积光谱调查工具，通过红移空间畸变研究声学震荡和结构增长，安装在亚利桑那基峰的 Mayall 望远镜上，覆盖 14000 平方度，具有 5000 个同时光谱的能力。