Advancing Exoplanet Transit Characterization through Machine Learning

In this study, we go beyond the usage of a single modeling approach and employ a range of scalable ML models, including Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), and Gradient Boosting (GB). However, to comprehensively evaluate the performance of these ML models, we compare their results with those obtained from the ExoRotGP model. By comparing the outcomes of these ML models with the reference GP results, we aim to rigorously assess their respective abilities in accurately extracting transit and rotation parameters from Kepler light curves. Specifically, we emphasize determining the rotation period of the host star for a given exoplanet. Through this meticulous comparative analysis, we seek to gain valuable insights into the strengths and limitations of different modeling approaches, thereby contributing to the advancement of exoplanet characterization techniques. This approach allows us to explore the diverse perspectives and potential synergies between the ML models and the ExoRotGP model, leading to a more comprehensive understanding of the underlying data and enhancing our ability to uncover important insights from exoplanetary systems.