Exoplanet Hunting in Deep Space with Machine Learning
Keywords:Astronomy, Exoplanet, Habitability, Kepler, Machine learning, NASA, SMOTE
This project focuses on the application of various machine learning algorithms on NASA’s Kepler data for prediction of exoplanet habitability disposition. A comparative study of the performance of various algorithms will also be performed. The results obtained will be used to identify algorithms which are suitable for performing prediction about exoplanets. It is the need of the hour to utilize machine learning to expedite the process of exoplanet detection. This will provide greater insights in the study of planet habitability, stellar bodies and the variety of exoplanets that exist in our galaxy. As space telescopes return new data the model can be further tuned for a further improvement of accuracy. The proposed model will be able to operate on data generated by different ground and space observatories and classify exoplanet candidates as habitable or non-habitable.
How to Cite
This work is licensed under a Creative Commons Attribution 4.0 International License.