Predicting Exoplanet Habitability Using Machine Learning

Biswas, Debayan (2024) Predicting Exoplanet Habitability Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

The study of exoplanets is a vital area for understanding the presence of life beyond the solar system. Despite having significant scientific achievements and findings in this field, there remains a significant gap in the development of methodologies to accurately predict and classify the habitability of exoplanets. The motivation of this study comes from the limitations of the present methodologies due to the presence of imbalance class and data scarcity in the data recorded due to the vastness of space. This project aims to overcome this problem by integrating data from the Transiting Exoplanet Survey Satellite (TESS) and the Planetary Habitability Laboratory (PHL) sources followed by the application of an extended Conditional Generative Adversarial Networks (cGANs) algorithm. This extended algorithm will lay forward the creation of a robust model to handle complex astronomical data by using a custom classifier XGBoost. The GANs will aid in generating real-life synthetic data thereby enhancing the existing dataset. The core findings of this research is to show the effectiveness of the cGAN in generating synthetic data and using custom classifier in predicting potentially habitable exoplanets. The result of the project show the the prediction accuracy achieved is at 96% that determine the accuracy and efficiency of the model. The contribution of this project can open a new chapter in this astronomical research domain by enhancing exoplanet research and thereby making way for future voyages toward our future destination.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Agarwal, Bharat UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QB Astronomy Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	14 Aug 2025 15:30
Last Modified:	14 Aug 2025 15:39
URI:	https://norma.ncirl.ie/id/eprint/8541

Actions (login required)

View Item