H  <scp>i</scp> 21-cm absorption spectra classification using machine learning

ABSTRACT H i 21-cm absorption, an extremely useful tool to study the cold atomic hydrogen gas, can arise either from the intervening galaxies along the line of sight towards the background radio source or from the radio source itself. Determining whether H i 21-cm absorption lines detected as part of large, blind surveys are ‘intervening’ or ‘associated’ using optical spectroscopy would be unfeasible. We therefore investigate a more efficient, machine learning (ML)-based method to classify H i 21-cm absorption lines. Using a sample of 118 known H i 21-cm absorption lines from the literature, we train six ML models (Gaussian naive Bayes, logistic regression, decision tree, random forest, support vector machine, and extreme gradient boosting) on the spectral parameters obtained by fitting the Busy function to the absorption spectra. We found that a random forest model trained on these spectral parameters gives the most reliable classification results, with an accuracy of 89 per cent, an $F_1$-score of 0.9, and an AUC score of 0.94. We note that the linewidth parameter $w_{20}$ is the most significant spectral parameter that regulates the classification performance of this model. Retraining this random forest model only with the linewidth and the integrated optical depth parameters yields an accuracy of 88 per cent, an $F_1$-score of 0.88, and an AUC score of 0.91. We have applied this retrained random forest model to predict the type of 30 new H i 21-cm absorption lines detected in recent blind surveys, viz. First Large Absorption Survey in H i, illustrating the potential of the techniques developed in this work for future large H i surveys with the Square Kilometre Array.