Identifying Exoplanets with Machine Learning Methods: A Preliminary Study

TL;DR

This study explores machine learning techniques to identify and classify exoplanets using NASA's Kepler datasets, achieving high accuracy and effective clustering, offering a promising alternative to traditional detection methods.

Contribution

It introduces the application of supervised and unsupervised machine learning models to exoplanet detection and classification, demonstrating high accuracy and effective clustering on NASA datasets.

Findings

Supervised models achieved over 88% accuracy in exoplanet classification.

Unsupervised clustering effectively grouped confirmed exoplanets.

Machine learning models show promise as efficient tools for exoplanet discovery.

Abstract

The discovery of habitable exoplanets has long been a heated topic in astronomy. Traditional methods for exoplanet identification include the wobble method, direct imaging, gravitational microlensing, etc., which not only require a considerable investment of manpower, time, and money, but also are limited by the performance of astronomical telescopes. In this study, we proposed the idea of using machine learning methods to identify exoplanets. We used the Kepler dataset collected by NASA from the Kepler Space Observatory to conduct supervised learning, which predicts the existence of exoplanet candidates as a three-categorical classification task, using decision tree, random forest, na\"ive Bayes, and neural network; we used another NASA dataset consisted of the confirmed exoplanets data to conduct unsupervised learning, which divides the confirmed exoplanets into different clusters, using k-means clustering. As a result, our models achieved accuracies of 99.06%, 92.11%, 88.50%, and 99.79%, respectively, in the supervised learning task and successfully obtained reasonable clusters in the unsupervised learning task.