Mapping the Universe: classifying galaxies and quasars through essential spectral features with machine learning
This is a work that implements spectra of distant celestial objects taken by the spectrograph of the DESI collaboration. It seeks to deal with the current problem of ambiguity in the classification of Seyfert-type galaxies, causars and stars. For this purpose, a set of spectrophotometric variables i...
- Autores:
-
Fajardo Poveda, Daniel Andrés
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2024
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/74561
- Acceso en línea:
- https://hdl.handle.net/1992/74561
- Palabra clave:
- Astronomia
Extragalactica
Galaxias
Quasares
Estrellas
Clasificadores
Fotometria
Espectroscopia
Espectros
DESI
Machine learning
Redshift
Física
- Rights
- openAccess
- License
- Attribution-NoDerivatives 4.0 International
| Summary: | This is a work that implements spectra of distant celestial objects taken by the spectrograph of the DESI collaboration. It seeks to deal with the current problem of ambiguity in the classification of Seyfert-type galaxies, causars and stars. For this purpose, a set of spectrophotometric variables is proposed and the best models for the creation of spectral classifiers are found. |
|---|