Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models

TL;DR

Astroconformer, a Transformer-based deep learning model, effectively analyzes stellar light curves to estimate stellar properties like surface gravity and oscillation frequencies, outperforming CNNs and traditional methods.

Contribution

This paper introduces Astroconformer, the first Transformer-based framework tailored for stellar light curve analysis, capturing long-range dependencies and phase information for improved stellar property inference.

Findings

Achieves RMSE of 0.017 dex for log g estimation in data-rich regimes.

Less than 2% median absolute error in ν_max estimation for 90-day light curves.

Outperforms CNNs and K-nearest neighbor models in accuracy.

Abstract

Stellar light curves contain valuable information about oscillations and granulation, offering insights into stars' internal structures and evolutionary states. Traditional asteroseismic techniques, primarily focused on power spectral analysis, often overlook the crucial phase information in these light curves. Addressing this gap, recent machine learning applications, particularly those using Convolutional Neural Networks (CNNs), have made strides in inferring stellar properties from light curves. However, CNNs are limited by their localized feature extraction capabilities. In response, we introduce $\textit{Astroconformer}$, a Transformer-based deep learning framework, specifically designed to capture long-range dependencies in stellar light curves. Our empirical analysis centers on estimating surface gravity ($\log g$), using a dataset derived from single-quarter Kepler light curves with $\log g$ values ranging from 0.2 to 4.4. $\textit{Astroconformer}$ demonstrates superior performance, achieving a root-mean-square-error (RMSE) of 0.017 dex at $\log g\approx3$ in data-rich regimes and up to 0.1 dex in sparser areas. This performance surpasses both K-nearest neighbor models and advanced CNNs. Ablation studies highlight the influence of receptive field size on model effectiveness, with larger fields correlating to improved results. $\textit{Astroconformer}$ also excels in extracting $\nu_{\max}$ with high precision. It achieves less than 2% relative median absolute error for 90-day red giant light curves. Notably, the error remains under 3% for 30-day light curves, whose oscillations are undetectable by a conventional pipeline in 30% cases. Furthermore, the attention mechanisms in $\textit{Astroconformer}$ align closely with the characteristics of stellar oscillations and granulation observed in light curves.