With the constant growth of objects in orbit, the monitoring and cataloging of space population is essential. Light curves obtained from ground stations support this point, providing valuable information about the object observed. From there the idea of using this data to identify an object through the correlation with another cataloged takes hold. This thesis focuses on the development of a tool for the analysis and correlation of two light curves, ARIEL. This tool is built through neural networks and declined in three strategies, each with its own goal: ROGUE, LINDEN and SIERRA. The light curves were retrieved via the database managed by the Mini-MegaTORTORA observatory and filtered using the Savitzky-Golay filter.
Con la costante crescita di oggetti messi in orbita, il monitoraggio e la catalogazione della popolazione spaziale è essenziale. Le curve di luce ottenute da stazioni di terra supportano questo punto, fornendo preziose informazioni sull’oggetto osservato. Da lì prende piede l’idea di utilizzare questi dati per identificare un oggetto attraverso la correlazione con un altro catalogato. Questa tesi si focalizza quindi sull’elaborazione di un tool per l’analisi e la correlazione di due curve di luce, ARIEL. Questo tool è costruito tramite reti neurali e declinato in tre strategie, ognuna con il proprio obiettivo: ROGUE, LINDEN e SIERRA. Le curve di luce sono state recuperate tramite il database gestito dall’osservatorio Mini-MegaTORTORA e ripulite tramite il filtro Savitzky-Golay .
Space object identification and correlation through AI-aided light curve feature extraction
BERTOLINI, CHIARA
2021/2022
Abstract
With the constant growth of objects in orbit, the monitoring and cataloging of space population is essential. Light curves obtained from ground stations support this point, providing valuable information about the object observed. From there the idea of using this data to identify an object through the correlation with another cataloged takes hold. This thesis focuses on the development of a tool for the analysis and correlation of two light curves, ARIEL. This tool is built through neural networks and declined in three strategies, each with its own goal: ROGUE, LINDEN and SIERRA. The light curves were retrieved via the database managed by the Mini-MegaTORTORA observatory and filtered using the Savitzky-Golay filter.File | Dimensione | Formato | |
---|---|---|---|
BERTOLINI_952823.pdf
Open Access dal 24/11/2023
Descrizione: Tesi di Laurea Magistrale
Dimensione
10.81 MB
Formato
Adobe PDF
|
10.81 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/197423