Archivio Istituzionale della RicercaWe demonstrate interconnected meshed optical networks as sensing-localization grid for earthquake early detection. We integrate noisy polarization evolution data induced by seven earthquakes, into a Waveplate model to enhance a machine-learning algorithm that accurately detects primary waves, improves urban safety and mimic real case scenarios.
Machine Learning-Driven Earthquake Early Warning Using Optical Fiber Mesh Networks / Awad, Hasan; Usmani, Fehmida; Virgillito, Emanuele; Bratovich, Rudi; Straullu, Stefano; Aquilino, Francesco; Proietti, Roberto; Pastorelli, Rosanna; Curri, Vittorio. - (2024), pp. 1-2. (Intervento presentato al convegno 2024 IEEE Photonics Conference, IPC 2024 tenutosi a Roma (Ita) nel 10-14 November, 2024) [10.1109/ipc60965.2024.10799809].
Machine Learning-Driven Earthquake Early Warning Using Optical Fiber Mesh Networks
Awad, Hasan;Usmani, Fehmida;Virgillito, Emanuele;Straullu, Stefano;Proietti, Roberto;Pastorelli, Rosanna;Curri, Vittorio
2024
Abstract
We demonstrate interconnected meshed optical networks as sensing-localization grid for earthquake early detection. We integrate noisy polarization evolution data induced by seven earthquakes, into a Waveplate model to enhance a machine-learning algorithm that accurately detects primary waves, improves urban safety and mimic real case scenarios.
| File | Dimensione | Formato | |
|---|---|---|---|
|
Machine_Learning-Driven_Earthquake_Early_Warning_Using_Optical_Fiber_Mesh_Networks.pdf
accesso riservato
Tipologia:
1. Preprint / submitted version [pre- review]
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
1.08 MB
Formato
Adobe PDF
|
1.08 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
IPC Machine Learning-Driven Earthquake Early Warning Using Optical Fiber Mesh Networks.pdf
accesso aperto
Descrizione: final post-refereeing author’s version without editorial layout
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
980.14 kB
Formato
Adobe PDF
|
980.14 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2997939