Identification of anomalous E+A galaxies in GAMA using an isolation forest

ABSTRACT We implement an outlier detection model, an Isolation Forest (iForest), to uncover anomalous objects in the Galaxy and Mass Assembly Fourth Data Release (GAMA DR4). The iForest algorithm is an unsupervised machine learning (ML) technique. The data we use are spectroscopic and photometric data from GAMA DR4, which compiles information for over 300 000 objects. We select two samples of galaxies to isolate, high signal-to-noise galaxies, to analyse the iForest’s robustness, and E+A galaxies, to study the extremes of their population. We result in six sub-samples of spectroscopic, photometric, and combined data isolations, finding 101 anomalous objects, 50 per cent of which have not been identified as outliers in other works. We also find a number of fringing errors and false emission lines, displaying the iForest’s potential in detecting these errors. We find anomalous E+A galaxies – that although selected in a ‘normal’ manner using low [O ii] and strong H δ absorption – are still star-forming, with strong H α emission. We propose two solutions to how these E+A galaxies are still star forming but also question if these galaxies can be truly classified as E+A galaxies. We suggest that small-scale interactions of gas-poor objects cause small star bursts, but the radiative pressure when high mass star form, expels the accreting material quicker than it can be accreted. We also suggest that the Jeans limit in our anomalous E+A galaxies is so low that it is simply not possible for O and B class stars to form, but it does not entirely prevent star formation.