Project description
Machine learning for enhanced solar activity predictions
Space weather refers to changes in the near-Earth environment caused by the Sun, which can disrupt satellites, navigation, aviation and power grids. Accurate forecasting is crucial for protecting infrastructure, but current methods often fall short. Supported by the Marie Skłodowska-Curie Actions programme, the SOFIA project will improve solar activity predictions using advanced machine learning, particularly variational autoencoders (VAEs). These models will create structured representations of solar active regions from NASA’s Solar Dynamics Observatory, linking magnetic features to solar eruptions. Additionally, sequential models will improve interpretability and track changes over time. The project will also analyse full-disk solar observations to integrate local and global factors affecting solar variability.
Objective
Space weather describes variable conditions in the near-Earth environment that can disrupt satellites, navigation and communication systems, aviation, and power grids, with cascading consequences for modern technologically-dependent society. The Sun is the primary driver of these disturbances, releasing bursts of radiation, energetic particles, and plasma through solar flares and coronal mass ejections. Reliable forecasts of such events are therefore critical to strengthen early-warning systems and safeguard European infrastructure, yet current approaches lack consistent parameters that capture how solar activity emerges and evolves across scales. This project integrates advanced machine learning methods to improve the description and prediction of solar activity. A central innovation is the extensive use of Variational Autoencoders (VAEs) for explainable ML-based parametrization of complex solar processes. First, VAEs will generate structured latent representations of solar active regions from multi-wavelength observations provided by NASA’s Solar Dynamics Observatory, delivering physically meaningful parameters that link magnetic morphology to the occurrence of eruptions. Weakly supervised and sequential models will then enhance interpretability and capture temporal evolution, while extensions to full-disk solar observations will integrate local and global drivers of solar variability. Finally, these data-driven representations will be coupled with geophysical models of the near-Earth environment, connecting solar drivers to response in interplanetary space and Earth’s atmosphere. By uniting physics-based and data-driven approaches, this work will lay the foundation for more accurate, reliable, and actionable space weather forecasts, strengthening resilience against solar-driven hazards.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
- natural sciences earth and related environmental sciences atmospheric sciences meteorology
- natural sciences physical sciences astronomy galactic astronomy solar physics
- natural sciences physical sciences astronomy galactic astronomy solar astronomy
- engineering and technology electrical engineering, electronic engineering, information engineering electrical engineering power engineering electric power transmission
- natural sciences computer and information sciences artificial intelligence machine learning
You need to log in or register to use this function
Keywords
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
-
HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA)
MAIN PROGRAMME
See all projects funded under this programme
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships
See all projects funded under this funding scheme
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
(opens in new window) HORIZON-MSCA-2025-PF
See all projects funded under this callCoordinator
Net EU financial contribution. The sum of money that the participant receives, deducted by the EU contribution to its linked third party. It considers the distribution of the EU financial contribution between direct beneficiaries of the project and other types of participants, like third-party participants.
14473 POTSDAM
Germany
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.