Galaxy Morphology and Quenching State Classification using ML models
This project investigates the effectiveness of different data modalities — tabular data (catalog features), image data (galaxy images), and their combination — in predicting galaxy morphology and quenching states.
By comparing models trained on individual vs. combined modalities, we aim to understand whether integration improves classification performance.
| Name | Student ID |
|---|---|
| Adam Aboushady | aha2003 |
| Ihsan Fazal | mf2056 |
| Janya Rathnakumar | jr2068 |
| Mustansir Eranpurwala | mte2000 |
| Vaishnavi Chintha | svc2000 |