In the power spectra of oscillating red giants, there are visually distinct features defining stars ascending the red giant branch from those that have commenced helium core burning. We train a 1D convolutional neural network by supervised learning to automatically learn these visual features from images of folded oscillation spectra. By training and testing on Kepler red giants, we achieve an accuracy of up to 99 per cent in separating helium-burning red giants from those ascending the red giant branch. The convolutional neural network additionally shows capability in accurately predicting the evolutionary states of 5379 previously unclassified Kepler red giants, by which we now have greatly increased the number of classified stars.

Cone search capability for table J/MNRAS/469/4578/test (*Population class predictions for 1008 Kepler red giants (test set))

Cone search capability for table J/MNRAS/469/4578/unclass (*Population class predictions for 7655 Kepler red giants (the unclassified set))