Using a neural network approach and starspots dependent models to predict effective temperatures and ages of young stars

This study presents a statistical approach to accurately predict the effective temperatures of pre-main sequence stars, which are necessary for determining stellar ages using the isochrone methodology and cutting-age starspots-dependent models. By training a Neural Network model on high-quality spectroscopic temperatures from the Gaia-ESO Survey as the response variable, and using photometric data from Gaia DR3 and 2MASS catalogs as explanatory variables, we implemented a methodology to accurately derive the effective temperatures of much larger populations of stars for which only photometric data are available. The model demonstrated robust performance for low-mass stars with temperatures below 7 000 K, including young stars, the primary focus of this work. Predicted temperatures were employed to construct Hertzsprung-Russell diagrams and to predict stellar ages of different young clusters and star forming regions through isochrone interpolation, achieving excellent agreement with spectroscopic-based ages and literature values derived from model-independent methods like lithium equivalent widths. The inclusion of starspot evolutionary models improved the age predictions, providing a more accurate description of stellar properties. Additionally, the results regarding the effective temperature and age predictions of the young clusters provide evidence for intrinsic age spreads in the youngest clusters, suggesting multiple formation events over time.