Unveiling Exoplanets Through the Power of ML: A Comparative Analysis of RandomForest and Gaussian Models

In recent years, the exploration of exoplanets has gained momentum due to the increasing volume of data collected from missions like Kepler. Machine learning (ML) techniques have proven to be valuable tools for efficiently analyzing and classifying exoplanet candidates. This study focuses on the application of ML models, specifically Random Forest and Gaussian methods, to identify exoplanets using the light curves obtained from Kepler's archived data.

The research aims to develop accurate and robust models capable of distinguishing exoplanets from other celestial objects. Feature engineering techniques are employed to extract relevant information from the light curves, including transit depth, transit duration, and periodicity patterns. These features serve as inputs for both the Random Forest and Gaussian models, enabling them to learn and generalize from the training data.

The Random Forest model, known for its ensemble-based approach, demonstrates exceptional performance in exoplanet identification. Its ability to capture complex relationships among features and make accurate predictions results in high precision and recall scores. On the other hand, the Gaussian method, which relies on probabilistic modeling, exhibits competitive results through a different classification approach.

The performance of the Random Forest and Gaussian models is compared using comprehensive evaluation metrics such as accuracy, precision, recall, and F1 score. The results indicate that the Random Forest model outperforms the Gaussian method in terms of precision and recall. This highlights the effectiveness of ensemble-based ML techniques for exoplanet identification tasks.

In conclusion, this study successfully demonstrates the utilization of ML models, specifically Random Forest and Gaussian methods, for exoplanet identification using Kepler's archived data and light curves. The Random Forest model emerges as the superior choice, achieving higher accuracy and recall rates in distinguishing exoplanets from other celestial objects. These findings contribute to the advancement of exoplanet research and pave the way for the development of more precise and efficient identification methods in the future.