Unveiling Hidden Lyman Alpha Emitters in the DESI DR1 Data

TL;DR

This paper introduces a CNN-based method to efficiently detect high-redshift Lyman alpha emitters in DESI DR1 data, significantly improving identification accuracy and enabling detailed astrophysical analysis.

Contribution

The authors develop and validate a machine learning model that detects LAEs with high purity and completeness, uncovering nearly 20,000 new LAEs in DESI spectra.

Findings

Achieved 95.2% purity and 95.9% completeness in LAE detection.

Detected 19,685 LAEs from approximately 2 million spectra in 12 minutes.

Composite spectrum reveals spectral features indicating astrophysical properties.

Abstract

We present an automatic method based on machine-learning convolutional neural network (CNN) architecture to detect Lyman alpha emitters (LAE) hidden in the Data Release 1 spectroscopic dataset of the Dark Energy Spectroscopic Instrument (DESI). Those LAEs mostly have incorrect redshift estimations because the current DESI pipeline is not designed to detect and measure the redshifts of galaxies at $z>2$. To uncover those sources, we first visually inspect thousands of DESI spectra and construct a sample, consisting of both LAEs and non-LAEs, for training and testing the CNN-based model to (1) detect LAEs in DESI spectra and (2) determine their Ly$\alpha$ redshifts. The final model yields $95.2\%$ purity and $95.9\%$ completeness for detecting LAEs. We apply this model to approximately $2\times10^{6}$ spectra of sources targeted as emission-line galaxies and detect 19,685 LAEs from $z\sim2$ to $3.5$ within 12 minutes with a single GPU, illustrating the high efficiency of this model for identifying LAEs. The detected LAEs are mostly at the bright end of the luminosity function with Ly$\alpha$ luminosity $L_{\rm Ly\alpha} \gtrsim 10^{43}$ erg/s. The high signal-to-noise composite spectrum of the detected LAEs further shows various spectral features, including P-Cygni profiles of metal lines and MgII emission lines, possible indicators of Lyman continuum escape fraction, revealing the rich astrophysical information in this LAE sample. Finally, this sample can be used to train and validate the pipelines for redshift determination of LAEs for the preparation of the DESI-II survey.