Astroconformer: Inferring Surface Gravity of Stars from Stellar Light Curves with Transformer
This work addresses the challenge of analyzing stellar light curves for asteroseismology, offering a more interpretable deep learning approach that could enhance future ground-based observations.
The paper tackles the problem of inferring stellar surface gravity from light curves by introducing Astroconformer, a Transformer-based model that outperforms state-of-the-art data-driven methods, as demonstrated on Kepler mission data and generalized to sparse cadence light curves from the Rubin Observatory.
We introduce Astroconformer, a Transformer-based model to analyze stellar light curves from the Kepler mission. We demonstrate that Astrconformer can robustly infer the stellar surface gravity as a supervised task. Importantly, as Transformer captures long-range information in the time series, it outperforms the state-of-the-art data-driven method in the field, and the critical role of self-attention is proved through ablation experiments. Furthermore, the attention map from Astroconformer exemplifies the long-range correlation information learned by the model, leading to a more interpretable deep learning approach for asteroseismology. Besides data from Kepler, we also show that the method can generalize to sparse cadence light curves from the Rubin Observatory, paving the way for the new era of asteroseismology, harnessing information from long-cadence ground-based observations.