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

TL;DR

This paper develops a CNN model inspired by QuasarNET to classify Lyman Break Galaxies and estimate their redshifts in DESI data, achieving significant performance improvements through data augmentation and hyperparameter tuning.

Contribution

It introduces a CNN architecture tailored for LBG classification and redshift regression, utilizing transfer learning and Bayesian optimization to enhance accuracy.

Findings

Achieved up to 26% improvement on Purity/Efficiency curve.

Model accuracy increased from 75% to 94%.

Effective data augmentation techniques expanded training data from 3,019 to over 66,000 samples.

Abstract

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.