Luminis Stellarum et Machina: Applications of Machine Learning in Light Curve Analysis

The rapid advancement of observational capabilities in astronomy has led to an exponential growth in the volume of light curve (LC) data, presenting both opportunities and challenges for time-domain astronomy. Traditional analytical methods often struggle to fully extract the scientific value of these vast datasets, especially as their complexity increases. Machine learning (ML) algorithms have become indispensable tools for analyzing light curves, offering the ability to classify, predict, discover patterns, and detect anomalies. Despite the growing adoption of ML techniques, challenges remain in LC classification, including class imbalance, noisy data, and interpretability of models. These challenges emphasize the importance of conducting a systematic review of ML algorithms specifically tailored for LC analysis. This survey provides a comprehensive overview of the latest ML techniques, summarizing their principles and applications in key astronomical tasks such as exoplanet detection, variable star classification, and supernova identification. It also discusses strategies to address the existing challenges and advance LC analysis in the near future. As astronomical datasets continue to grow, the integration of ML and deep learning (DL) techniques will be essential for unlocking the full scientific potential of LC data in the era of astronomical big data.