Tools
Tools
Ay, Buse (2024) Comparative Analysis of Machine Learning and Neural Network Approaches for Exoplanet Identification. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (845kB) | Preview |
Abstract
Several missions collect vast amounts of data from space every day. One of the purposes of that is to unravel the mystery of exoplanets. Due to the volume and the complexity of data, machine learning, and deep learning methods became popular for exoplanet identification. In this study, we used flux entries for multiple stars from Kepler Mission and applied a range of machine learning and deep learning algorithms, including K-Nearest Neighbors (KNN), Decision Tree, Logistic Regression, AdaBoost, XGBoost, Fully Connected Neural Networks, 1D Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) network. For the evaluation accuracy, precision, recall, and F-1 score metrics were used. Results indicate that ensemble methods worked better on this specific data. AdaBoost and XGBoost, outperformed neural networks being more straightforward. The data used in this project is noisy, and because of that neural networks might learn noises instead of the flux patterns. The importance of model selection depending on the dataset for the identification of exoplanets is highlighted in this paper.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Jain, Mayank 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 Artificial Intelligence |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 17 Jun 2025 18:26 |
| Last Modified: | 17 Jun 2025 18:26 |
| URI: | https://norma.ncirl.ie/id/eprint/7897 |
Actions (login required)
 |
View Item |