Speaker
Description
The rapid progress in astronomical observation technologies has led to an enormous increase in light-curve data, bringing both exciting scientific opportunities and major challenges for time-domain astronomy. Traditional analysis techniques often fall short of fully exploiting the scientific potential of these large and increasingly complex datasets. As a result, machine learning algorithms have become essential tools for classifying, forecasting, and identifying patterns or anomalies in light curves. My research focuses on advancing our understanding of the formation and evolution of hot subluminous stars – hot, compact, and evolved stellar objects – by investigating their photometric variability using multi-band time-series data from multiple surveys and applying modern machine learning methods. The first part of my talk will present statistical and machine learning approaches developed to efficiently handle unevenly sampled light curves in large stellar samples. I will demonstrate how unsupervised learning techniques can detect and cluster different types of variability in irregularly sampled datasets. In the second part, I will discuss how multi-band observations from the BlackGEM telescope array support pulsation mode identification in compact pulsators such as hot subdwarfs and pre-white dwarfs. Together, these studies provide a foundation for future machine-learning-driven research in time-domain astronomy and contribute to a deeper understanding of the evolution of compact, evolved stars.