The study of the cosmos through large-scale surveys such as J-PLUS and Gaia generates vast amounts of astronomical data, ushering astronomy into the era of big data. These observations span a wide range of energies, from gamma rays to radio waves, producing petabytes of data that require advanced techniques for efficient processing and analysis. The application of artificial intelligence (AI) and machine learning, particularly in the estimation of astrophysical parameters like stellar temperature, luminosity, and radius, has become crucial in this context. Models such as XGBoost and Random Forest are increasingly used to predict these parameters, aiding in the understanding of stellar evolution and galactic dynamics. However, the success of these models is contingent on the quality of the data, making preprocessing a critical step. This chapter focuses on data cleaning, correction of interstellar extinction, and feature engineering to enhance the accuracy of machine learning predictions. By integrating AI, this work demonstrates how modern techniques can transform our understanding of the universe.