Blind QSO reconstruction challenge: Exploring methods to reconstruct the Ly$\alpha$ emission line of QSOs

TL;DR

This study compares various methods for reconstructing the Lyα emission line in high-redshift QSOs, revealing that machine learning approaches excel in predictions but underestimate uncertainties, while spectral decomposition methods perform better overall.

Contribution

It provides a blind, unbiased comparison of multiple Lyα reconstruction pipelines on a uniform dataset, highlighting their relative strengths and weaknesses.

Findings

Machine learning methods give strong predictions but underestimate uncertainties.

Spectral decomposition approaches generally outperform other methods.

Reconstruction performance is consistent across different observational datasets.

Abstract

Reconstructing the intrinsic Ly$\alpha$ line flux from high-$z$ QSOs can place constraints on the neutral hydrogen content of the intergalactic medium during reionisation. There are now $\gtrsim10$ different Ly$\alpha$ reconstruction pipelines using different methodologies to predict the Ly$\alpha$ line flux from correlations with the spectral information redward of Ly$\alpha$. However, there have been few attempts to directly compare the performance of these pipelines. Therefore, we devised a blind QSO challenge to compare these reconstruction pipelines on a uniform set of objects. Each author was provided de-identified, observed rest-frame QSO spectra with spectral information only redward of 1260\AA\ rest-frame to ensure unbiased reconstruction. We constructed two samples of 30 QSOs, from X-Shooter and SDSS both spanning $3.5<z<4.5$. Importantly, the purpose of this comparison study was not to champion a single, best performing reconstruction pipeline but rather to explore the relative performance of these pipelines over a range of QSOs with broad observational characteristics to infer general trends. In summary, we find machine learning approaches in general provide the strongest ``best guesses" but underestimate the accompanying statistical uncertainty, although these can be recalibrated, whilst pipelines that decompose the spectral information, for example principal component or factor analysis generally perform better at predicting the Ly$\alpha$ profile. Further, we found that reconstruction pipelines trained on SDSS QSOs performed similarly on average for both the X-Shooter and SDSS samples indicating no discernible biases owing to differences in the observational characteristics of the training set or QSO being reconstructed, although the recovered distributions of reconstructions for X-Shooter were broader likely due to an increased fraction of outliers.