The Physics of Solar Prominences: an AI/ML approach

Solar prominences are observed as large amount of cool material suspended into the solar atmosphere. There is a large variety of structures and evolution from short-lived erupting prominences to quiet prominences. Prominences are observed on the limb of the Sun and are injecting mass in the solar system through Coronal Mass Ejections (CMEs). You will use the capabilities of the NASA Solar Dynamics Observatory (SDO) Atmospheric Imaging Assembly (AIA) to observe and analyse the properties of prominences in time. SDO/AIA observations have now covered a full solar cycle (about 11 years) providing a huge amount of data (100 TB/year). You will address the following scientific questions that Artificial Intelligence (AI) and Machine Learning (ML) approaches could help to answer:

What is the magnetic structure of prominences?
Is there a single mechanism characterising prominence eruptions? What is the origin of prominence eruption and their consequences?
The aim is to produce a comprehensive survey of solar prominences, assimilating their physical properties into an open-access database. The project is two-fold:

Developing an algorithm based on AI/ML methods to extract the properties of prominences using NASA SDO/AIA data, and building an open-access database;
Performing a statistical analysis of prominences properties to determine the mechanism(s) of eruptions, and the variations during the solar cycle.