By precisely describing the planetary conditions and related properties of habitable exoplanets, AI algorithms can improve their identification and analysis.

This research focuses on the application of Artificial Intelligence (AI) to identify and evaluate the potential for habitability of exoplanets. It aims to train AI models capable of filtering exoplanets from a given dataset and further categorizing their potential for habitability on a scale depending on various planetary conditions. It questions how various crucial factors such as the radiative flux and the eccentricity of a planet affect its ability to support life. To achieve these goals, various AI models were systematically tested and the highest accuracy (~97%) was achieved using a Random Forest Classifier for both exoplanet detection and habitability potential. The study also discusses the importance of the Habitable Zone and liquid water in sustaining life. The data used is from NASA's Kepler Cumulative dataset. The research highlights the benefits of employing AI models to assess large datasets of exoplanets for the exploration of distant planetary systems.