Using deep learning to predict solar explosions using magnetograms
Solar activities, especially solar explosions, have a significant impact on some important technologies used on Earth, e.g., energy transmission networks and communications. Depending on the class of the explosion, the consequences can be hazardous. Therefore, when forecasting of solar explosions, e...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Online |
| Language: | English |
| Published: |
Universidade Estadual de Campinas
2019
|
| Subjects: | |
| Online Access: | https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/1036 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Solar activities, especially solar explosions, have a significant impact on some important technologies used on Earth, e.g., energy transmission networks and communications. Depending on the class of the explosion, the consequences can be hazardous. Therefore, when forecasting of solar explosions, earlier we can take actions to mitigate their impact on the affected technologies on Earth. In this work, we applied Deep Learning techniques to classify solar magnetograms, which indicate the class of a solar explosion. The classification of such images may help to anticipate the phenomenon. The results show a 97% of accuracy for the magnetograms classification. |
|---|---|
| ISSN: | 2596-1969 |
