Artificial Intelligence Could Have Predicted All Space Weather Events Associated with the May 2024 Superstorm
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912203013095424 |
|---|---|
| author | Guastavino, Sabrina Legnaro, Edoardo Massone, Anna Maria Piana, Michele |
| author_facet | Guastavino, Sabrina Legnaro, Edoardo Massone, Anna Maria Piana, Michele |
| contents | Space weather, driven by solar flares and Coronal Mass Ejections (CMEs), poses significant risks to technological systems. Accurately forecasting these events and their impact on Earth's magnetosphere remains a challenge because of the complexity of solar-terrestrial interactions. This study applied artificial intelligence (AI) to predict the chain of events associated with the May $2024$ superstorm, including solar flares from NOAA active region 13644, Earth-directed CMEs, and a violent geomagnetic storm. Using magnetogram cut-outs, a Vision Transformer was able to classify the evolution of the active region morphologies, and a video-based deep learning method predicted the occurrence of solar flares; a physics-driven model improved the precision of CME travel-time prediction using coronal observations and solar wind measurements; and a data-driven method exploited these in situ measurements to sound alerts of the geomagnetic storm unrolled over time. The results showed unprecedented accuracy in predicting CME arrival with uncertainty as small as one minute. Moreover, these AI models outperformed traditional methods in predicting solar flares occurrences, onset, and recovery phases of the geomagnetic storm. These findings highlight the impressive potential of AI for space weather forecasting and as a tool to mitigate the impact of extreme solar events on critical infrastructure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14684 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Artificial Intelligence Could Have Predicted All Space Weather Events Associated with the May 2024 Superstorm Guastavino, Sabrina Legnaro, Edoardo Massone, Anna Maria Piana, Michele Solar and Stellar Astrophysics Space Physics 68T07 Space weather, driven by solar flares and Coronal Mass Ejections (CMEs), poses significant risks to technological systems. Accurately forecasting these events and their impact on Earth's magnetosphere remains a challenge because of the complexity of solar-terrestrial interactions. This study applied artificial intelligence (AI) to predict the chain of events associated with the May $2024$ superstorm, including solar flares from NOAA active region 13644, Earth-directed CMEs, and a violent geomagnetic storm. Using magnetogram cut-outs, a Vision Transformer was able to classify the evolution of the active region morphologies, and a video-based deep learning method predicted the occurrence of solar flares; a physics-driven model improved the precision of CME travel-time prediction using coronal observations and solar wind measurements; and a data-driven method exploited these in situ measurements to sound alerts of the geomagnetic storm unrolled over time. The results showed unprecedented accuracy in predicting CME arrival with uncertainty as small as one minute. Moreover, these AI models outperformed traditional methods in predicting solar flares occurrences, onset, and recovery phases of the geomagnetic storm. These findings highlight the impressive potential of AI for space weather forecasting and as a tool to mitigate the impact of extreme solar events on critical infrastructure. |
| title | Artificial Intelligence Could Have Predicted All Space Weather Events Associated with the May 2024 Superstorm |
| topic | Solar and Stellar Astrophysics Space Physics 68T07 |
| url | https://arxiv.org/abs/2501.14684 |