SIMBAD references

Spica (α Virginis), a massive binary star system, offers insights into stellar evolution. Its orbital evolution, governed by the apsidal motion constant, reveals critical details about the stellar interior. However, calculating this constant using Modules for Experiments in Stellar Astrophysics (MESA) simulations is computationally demanding. To address this, we employed machine learning (ML) and deep learning (DL) methods to efficiently predict the apsidal constant. Random Forest and Recursive Neural Network emerged as the most effective ML and DL models, respectively, with luminosity, age, and temperature identified as key features. Our ensemble voting regressor, integrating ML and DL approaches, achieved superior accuracy. MESA models are consistent with recent constraints on Spica A's effective temperature, age, luminosity, and apsidal constant. This work promotes the potential of ML and DL in stellar research, advancing the understanding of the apsidal constant through stellar evolution.