Archivio Istituzionale della RicercaWe apply transfer learning with an LSTM-attention model, trained on simulated earthquake SOP data and tested on experimentally emulated data over a 38 km deployed fiber link, achieving 98% accuracy in early earthquake detection
Experimental Validation for Early Earthquake Detection Using Transfer Learning / Awad, Hasan; Usmani, Fehmida; Straullu, Stefano; Bratovich, Rudi; Virgillito, Emanuele; Aquilino, Francesco; Proietti, Roberto; Curri, Vittorio. - (2025), pp. 1-3. (Intervento presentato al convegno 2025 Optical Fiber Communications Conference and Exhibition (OFC) tenutosi a San Francisco (USA) nel 30 March - 03 April 2025).
Experimental Validation for Early Earthquake Detection Using Transfer Learning
Awad, Hasan;Usmani, Fehmida;Straullu, Stefano;Virgillito, Emanuele;Proietti, Roberto;Curri, Vittorio
2025
Abstract
We apply transfer learning with an LSTM-attention model, trained on simulated earthquake SOP data and tested on experimentally emulated data over a 38 km deployed fiber link, achieving 98% accuracy in early earthquake detection
| File | Dimensione | Formato | |
|---|---|---|---|
|
Experimental_Validation_for_Early_Earthquake_Detection_Using_Transfer_Learning.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
705.67 kB
Formato
Adobe PDF
|
705.67 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
Experimental Validation Using Transfer Learning for Early Earthquake Detection.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
687.53 kB
Formato
Adobe PDF
|
687.53 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/11583/3002533