Extraction of Physical Parameters of RRab Variables using Neural Network based Interpolator

Understanding the physical properties of RR Lyrae stars is crucial for probing their pulsation and evolutionary states. In this talk, I will present a machine learning framework that employs feedforward artificial neural networks (ANNs) to estimate key stellar parameters—mass, luminosity, effective temperature, and metallicity—directly from TESS light curves. The model is trained on a synthetic grid of RRab light curves generated from hydrodynamical pulsation models. It is validated using self-inversion tests and then applied to observed TESS RRab stars after appropriate preprocessing. Our method produces an empirical period-luminosity-metallicity (PLZ) relation and demonstrates that ANN-based inversion of single-band photometry is a promising alternative to traditional techniques. I will also briefly discuss the potential extension of this method to other classes of pulsating stars.