Mira Variables are a type of red pulsating stars with long periods, whose light curve shapes are of great interest for this work. The aim of my project is to analyse their properties (period and amplitude, for example) along with their morphology with Machine Learning algorithms, such as Random Forest, XGBoost and Neural Network, in order to classify them into C-rich/O-rich categories without the need of a spectroscopic or photometric follow-up. The dataset was retrieved from OGLE III catalogue.
Le variabili MIra sono un tipo di stelle pulsanti rosse con lunghi periodi, le cui forme della curva di luce sono di grande interesse per questo lavoro. Il fine del mio progetto è analizzare le loro proprietà (periodo e ampiezza, per esempio), insieme alla loro morfologia, con algoritmi di Machine Learning, come Random Forest, XGBoost e Neural Network, così da classificarle nelle categorie C-rich/O-rich senza performare un follow-up spettroscopico o fotometrico. Il dataset proviene dal catalogo di OGLE III.
Investigating Mira Variables by their light curve shapes with Machine Learning
NARDO, LINDA
2023/2024
Abstract
Mira Variables are a type of red pulsating stars with long periods, whose light curve shapes are of great interest for this work. The aim of my project is to analyse their properties (period and amplitude, for example) along with their morphology with Machine Learning algorithms, such as Random Forest, XGBoost and Neural Network, in order to classify them into C-rich/O-rich categories without the need of a spectroscopic or photometric follow-up. The dataset was retrieved from OGLE III catalogue.File | Dimensione | Formato | |
---|---|---|---|
Nardo_Linda.pdf
accesso riservato
Dimensione
4.27 MB
Formato
Adobe PDF
|
4.27 MB | Adobe PDF |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/64070