Predicting the Neutral Hydrogen Content of Galaxies From Optical Data Using Machine Learning

TL;DR

This paper presents a machine learning framework trained on simulations to predict galaxy HI content from optical and environmental data, achieving high accuracy at low redshift and useful predictions for upcoming surveys.

Contribution

The study introduces a novel machine learning approach trained on cosmological simulations to accurately predict galaxy HI content using optical and environmental features.

Findings

Random forest achieves the highest correlation coefficient (>0.9) at z=0.

Prediction accuracy declines with increasing redshift, limiting utility beyond z~1.

The method performs well on real survey data, with RMSE around 0.28 when trained on RESOLVE data.

Abstract

We develop a machine learning-based framework to predict the HI content of galaxies using more straightforwardly observable quantities such as optical photometry and environmental parameters. We train the algorithm on z=0-2 outputs from the Mufasa cosmological hydrodynamic simulation, which includes star formation, feedback, and a heuristic model to quench massive galaxies that yields a reasonable match to a range of survey data including HI. We employ a variety of machine learning methods (regressors), and quantify their performance using the root mean square error ({\sc rmse}) and the Pearson correlation coefficient (r). Considering SDSS photometry, 3$^{rd}$ nearest neighbor environment and line of sight peculiar velocities as features, we obtain r $> 0.8$ accuracy of the HI-richness prediction, corresponding to {\sc rmse}$<0.3$. Adding near-IR photometry to the features yields some improvement to the prediction. Compared to all the regressors, random forest shows the best performance, with r $>0.9$ at $z=0$, followed by a Deep Neural Network with r $>0.85$. All regressors exhibit a declining performance with increasing redshift, which limits the utility of this approach to $z\la 1$, and they tend to somewhat over-predict the HI content of low-HI galaxies which might be due to Eddington bias in the training sample. We test our approach on the RESOLVE survey data. Training on a subset of RESOLVE data, we find that our machine learning method can reasonably well predict the HI-richness of the remaining RESOLVE data, with {\sc rmse}$\sim0.28$. When we train on mock data from Mufasa and test on RESOLVE, this increases to {\sc rmse}$\sim0.45$. Our method will be useful for making galaxy-by-galaxy survey predictions and incompleteness corrections for upcoming HI 21cm surveys such as the LADUMA and MIGHTEE surveys on MeerKAT, over regions where photometry is already available.