Using Multivariate Imputation by Chained Equations to Predict Redshifts of Active Galactic Nuclei

TL;DR

This paper demonstrates that using the MICE imputation method to handle missing data significantly improves machine learning models' ability to predict the redshifts of active galactic nuclei from large survey data.

Contribution

It introduces the application of MICE for imputing missing data in AGN redshift prediction, enhancing ML model accuracy in astronomical datasets.

Findings

MICE effectively imputes 24% missing data in the 4LAC catalog.

Imputation with MICE improves ML redshift estimation accuracy.

The approach facilitates better utilization of incomplete astronomical data.

Abstract

Redshift measurement of active galactic nuclei (AGNs) remains a time-consuming and challenging task, as it requires follow up spectroscopic observations and detailed analysis. Hence, there exists an urgent requirement for alternative redshift estimation techniques. The use of machine learning (ML) for this purpose has been growing over the last few years, primarily due to the availability of large-scale galactic surveys. However, due to observational errors, a significant fraction of these data sets often have missing entries, rendering that fraction unusable for ML regression applications. In this study, we demonstrate the performance of an imputation technique called Multivariate Imputation by Chained Equations (MICE), which rectifies the issue of missing data entries by imputing them using the available information in the catalog. We use the Fermi-LAT Fourth Data Release Catalog (4LAC) and impute 24% of the catalog. Subsequently, we follow the methodology described in Dainotti et al. (2021) and create an ML model for estimating the redshift of 4LAC AGNs. We present results which highlight positive impact of MICE imputation technique on the machine learning models performance and obtained redshift estimation accuracy.