Exoplanet Detection using Machine Learning

Using data from NASA’s Kepler Space Telescope, this project compares conventional supervised learning algorithms for the classification of exoplanets. Accurately separating real exoplanet signals from false positives using a variety of high-level astronomical features is the difficult part. This dataset was used to train and evaluate Random Forest, Decision Tree, SVM, Logistic Regression, and Naive Bayes. Finding the most effective and reliable model for this classification task was the main objective. With the best accuracy and balanced ability to detect real exoplanets, the Random Forest Classifier showed promise for automating candidate evaluation. Key terms: NASA, Exoplanet, TESS, Random Forest, Naïve Bayes, Machine Learning.