Leveraging Deep Learning for Time Series Extrinsic Regression in predicting photometric metallicity of Fundamental-mode RR Lyrae Stars

TL;DR

This study explores applying deep-learning techniques, particularly advanced neural-network architectures, in predicting photometric metallicity from time-series data, and underscores the importance of deep learning in astronomical research, particularly with large datasets from missions like Gaia.

Abstract

Astronomy is entering an unprecedented era of Big Data science, driven by missions like the ESA's Gaia telescope, which aims to map the Milky Way in three dimensions. Gaia's vast dataset presents a monumental challenge for traditional analysis methods. The sheer scale of this data exceeds the capabilities of manual exploration, necessitating the utilization of advanced computational techniques. In response to this challenge, we developed a novel approach leveraging deep learning to estimate the metallicity of fundamental mode (ab-type) RR Lyrae stars from their light curves in the Gaia optical G-band. Our study explores applying deep learning techniques, particularly advanced neural network architectures, in predicting photometric metallicity from time-series data. Our deep learning models demonstrated notable predictive performance, with a low mean absolute error (MAE) of 0.0565, the root mean square error (RMSE) achieved is 0.0765 and a high $R^2$ regression performance of 0.9401 measured by cross-validation. The weighted mean absolute error (wMAE) is 0.0563, while the weighted root mean square error (wRMSE) is 0.0763. These results showcase the effectiveness of our approach in accurately estimating metallicity values. Our work underscores the importance of deep learning in astronomical research, particularly with large datasets from missions like Gaia. By harnessing the power of deep learning methods, we can provide precision in analyzing vast datasets, contributing to more precise and comprehensive insights into complex astronomical phenomena.

Figures (6)

• Figure S1: Phase-Folded and Phase-Aligned G-band Light Curves of 6002 RRab Stars. The two-dimensional plot depicts the phase and magnitude of G-band light curves for all the RRab stars, showcasing their characteristics after phase-folding and alignment.
• Figure S2: The two-dimensional representation illustrates the phase and magnitude of G-band light curves following the application of the Smoothing Spline method.
• Figure S3: The distribution of metallicity of 6002 RRab stars in our dataset along with their respective sample weights is illustrated. Histograms are marked by blue bars, while kernel density estimates of the [Fe/H] values are represented by green curves. Black symbols denote the (normalized) weights derived from the inverse of the density. The final sample weights are denoted by blue points.
• Figure S4: Graphic Representation of the GRU Model. The picture illustrates the layered structure of the GRU model, detailing the arrangement and interactions of the GRU layers, including input, hidden, and output layer (Dense layer).
• Figure S5: Training loss (red) versus validation loss (green) for each cross-validation folds (5). The plot illustrates the consistency between training and validation performance, indicating the model's ability to generalize well.