Deep Learning Classification in Asteroseismology Using an Improved Neural Network: Results on 15000 Kepler Red Giants and Applications to K2 and TESS Data

TL;DR

This paper presents an improved deep learning neural network that accurately classifies the evolutionary states of red giants from asteroseismic spectra, including new classifications for thousands of Kepler stars and robustness to data quality issues.

Contribution

An enhanced convolutional neural network model tailored for classifying red giant evolutionary states, applicable to data from Kepler, K2, TESS, and PLATO missions, with extensive new classifications and robustness.

Findings

Classified 14,983 Kepler red giants, including 4,263 newly classified.

Achieved high accuracy even with low signal-to-noise data.

Demonstrated robustness to incorrect labels and suboptimal data quality.

Abstract

Deep learning in the form of 1D convolutional neural networks have previously been shown to be capable of efficiently classifying the evolutionary state of oscillating red giants into red giant branch stars and helium-core burning stars by recognizing visual features in their asteroseismic frequency spectra. We elaborate further on the deep learning method by developing an improved convolutional neural network classifier. To make our method useful for current and future space missions such as K2, TESS and PLATO, we train classifiers that are able to classify the evolutionary states of lower frequency resolution spectra expected from these missions. Additionally, we provide new classifications for 8633 Kepler red giants, out of which 426 have previously not been classified using asteroseismology. This brings the total to 14983 Kepler red giants classified with our new neural network. We also verify that our classifiers are remarkably robust to suboptimal data, including low signal-to-noise and incorrect training truth labels.