Global Navigation Satellite System Ionospheric Seismology investigates the ionospheric response to earthquakes and tsunamis. These events are known to generate Traveling Ionospheric Disturbances (TIDs) that can be detected through GNSS-derived Total Electron Content (TEC) observations. Real-time TID identification provides a method for tsunami detection, improving tsunami early warning systems (TEWS) by extending coverage to open-ocean regions where buoy-based warning systems are impractical. Scalable and automated TID detection is, hence, essential for TEWS augmentation. In this work, we present an innovative approach to perform automatic real-time TID monitoring and detection, using deep learning insights. We utilize Gramian Angular Difference Fields (GADFs), a technique that transforms time-series into images, in combination with Convolutional Neural Networks (CNNs), starting from VARION (Variometric Approach for Real-time Ionosphere Observation) real-time TEC estimates. We select four tsunamigenic earthquakes that occurred in the Pacific Ocean: the 2010 Maule earthquake, the 2011 Tohoku earthquake, the 2012 Haida-Gwaii, the 2015 Illapel earthquake. The first three events are used for model training, whereas the out-of-sample validation is performed on the last one. The presented framework, being perfectly suitable for real-time applications, achieves 91.7% of F1 score and 84.6% of recall, highlighting its potential. Our approach to improve false positive detection, based on the likelihood of a TID at each time step, ensures robust and high performance as the system scales up, integrating more data for model training. This research lays the foundation for incorporating deep learning into real-time GNSS-TEC analysis, offering a joint and substantial contribution to TEWS progression.Global Navigation Satellite System Ionospheric Seismology investigates how the ionosphere responds to earthquakes and tsunamis, detecting TIDs through GNSS-derived TEC observations. Real-time TID identification aids tsunami detection, enhancing early warning systems by extending coverage to open-ocean regions. Automated TID detection is crucial for early warning system improvement. In this study, we propose an innovative approach using deep learning insights to perform automatic real-time TID monitoring and detection. We leverage GADFs and CNNs with VARION real-time TEC estimates. We train the model on four tsunamigenic earthquakes in the Pacific Ocean and validate it on an out-of-sample event. The framework achieves promising performance metrics, highlighting its potential for real-time applications. Our approach improves false positive detection, ensuring robustness and scalability as the system integrates more data for training. This research paves the way for integrating deep learning into real-time GNSS-TEC analysis, contributing significantly to the advancement of early warning systems.The proposed deep learning-based framework can detect earthquake and tsunami induced ionospheric perturbations in Total Electron Content observations We used a multi-event approach, focusing on the Pacific area, to train and to test the framework, achieving 91% of F1 score and 84% of recall The framework is well-suited for real-time applications, making it readily deployable to enhance tsunami early warning systems

Exploring AI Progress in GNSS Remote Sensing: A Deep Learning Based Framework for Real‐Time Detection of Earthquake and Tsunami Induced Ionospheric Perturbations / Ravanelli, Michela; Constantinou, Valentino; Liu, Hamlin; Bortnik, Jacob. - In: RADIO SCIENCE. - ISSN 0048-6604. - 59:9(2024). [10.1029/2024rs008016]

Exploring AI Progress in GNSS Remote Sensing: A Deep Learning Based Framework for Real‐Time Detection of Earthquake and Tsunami Induced Ionospheric Perturbations

Ravanelli, Michela
;
2024

Abstract

Global Navigation Satellite System Ionospheric Seismology investigates the ionospheric response to earthquakes and tsunamis. These events are known to generate Traveling Ionospheric Disturbances (TIDs) that can be detected through GNSS-derived Total Electron Content (TEC) observations. Real-time TID identification provides a method for tsunami detection, improving tsunami early warning systems (TEWS) by extending coverage to open-ocean regions where buoy-based warning systems are impractical. Scalable and automated TID detection is, hence, essential for TEWS augmentation. In this work, we present an innovative approach to perform automatic real-time TID monitoring and detection, using deep learning insights. We utilize Gramian Angular Difference Fields (GADFs), a technique that transforms time-series into images, in combination with Convolutional Neural Networks (CNNs), starting from VARION (Variometric Approach for Real-time Ionosphere Observation) real-time TEC estimates. We select four tsunamigenic earthquakes that occurred in the Pacific Ocean: the 2010 Maule earthquake, the 2011 Tohoku earthquake, the 2012 Haida-Gwaii, the 2015 Illapel earthquake. The first three events are used for model training, whereas the out-of-sample validation is performed on the last one. The presented framework, being perfectly suitable for real-time applications, achieves 91.7% of F1 score and 84.6% of recall, highlighting its potential. Our approach to improve false positive detection, based on the likelihood of a TID at each time step, ensures robust and high performance as the system scales up, integrating more data for model training. This research lays the foundation for incorporating deep learning into real-time GNSS-TEC analysis, offering a joint and substantial contribution to TEWS progression.Global Navigation Satellite System Ionospheric Seismology investigates how the ionosphere responds to earthquakes and tsunamis, detecting TIDs through GNSS-derived TEC observations. Real-time TID identification aids tsunami detection, enhancing early warning systems by extending coverage to open-ocean regions. Automated TID detection is crucial for early warning system improvement. In this study, we propose an innovative approach using deep learning insights to perform automatic real-time TID monitoring and detection. We leverage GADFs and CNNs with VARION real-time TEC estimates. We train the model on four tsunamigenic earthquakes in the Pacific Ocean and validate it on an out-of-sample event. The framework achieves promising performance metrics, highlighting its potential for real-time applications. Our approach improves false positive detection, ensuring robustness and scalability as the system integrates more data for training. This research paves the way for integrating deep learning into real-time GNSS-TEC analysis, contributing significantly to the advancement of early warning systems.The proposed deep learning-based framework can detect earthquake and tsunami induced ionospheric perturbations in Total Electron Content observations We used a multi-event approach, focusing on the Pacific area, to train and to test the framework, achieving 91% of F1 score and 84% of recall The framework is well-suited for real-time applications, making it readily deployable to enhance tsunami early warning systems
2024
gnss-total electron content observations; earthquake and tsunami-induced ionospheric disturbances; deep learning; convolutional neural networks; tsunami early warning systems (TEWS); ai4 Geodesy
01 Pubblicazione su rivista::01a Articolo in rivista
Exploring AI Progress in GNSS Remote Sensing: A Deep Learning Based Framework for Real‐Time Detection of Earthquake and Tsunami Induced Ionospheric Perturbations / Ravanelli, Michela; Constantinou, Valentino; Liu, Hamlin; Bortnik, Jacob. - In: RADIO SCIENCE. - ISSN 0048-6604. - 59:9(2024). [10.1029/2024rs008016]
File allegati a questo prodotto
File Dimensione Formato  
Ravanelli_Exploring-AI-Progress_2024.pdf

accesso aperto

Note: Articolo
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 2.91 MB
Formato Adobe PDF
2.91 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1724198
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 1
social impact