Deep learning for prediction of geomagnetic events

Eruptions on the solar surface may give rise to coronal mass ejections, leading to significant magnetic fields that may disrupt the operation of electronic devices on the Earth or in space, including satellites. The activity has the objective of employing artificial intelligence, and in particular deep neural networks, in order to design systems able to predict and detect coronal mass ejections. The detection can be performed using images of the solar corona, as well as measurements from in-situ magnetic sensors. This activity is carried out in collaboration with the Astronomic Observatory in Pino Torinese, exploiting the large amount of data logged over several years, as well as ground truth data related to observed coronal mass ejections.

Link:

ERC Sector:

  • PE7_7 Signal processing

Keywords:

  • Artificial neural networks
  • Astrophysics

Gruppi di ricerca

Persone di riferimento