Solar Flares and CMEs: Observations, Theory and Machine Learning

Topic: Solar Physics

Session Title: Solar Flares and CMEs: Observations, Theory and Machine Learning


In today’s space-based technological era, the immediate and profound impacts of solar flares and coronal mass ejections (CMEs) on the interplanetary and geospace cannot be understated. Understanding the intricate mechanisms behind these powerful solar phenomena and devising effective prediction methods have become pivotal.

To address this challenge, our research community now engages with a wide spectrum of data, embracing varied physical phenomena, features, and predictive indicators.
Methodologies encompass a diverse range of data sources, from high-resolution solar images for gathering information about solar surface features, active regions, and potential eruption locations. Additionally, solar magnetograms, radio observations for monitoring plasma distributions, coronagraph images, and solar wind monitoring data are employed. This wealth of data also fuels advancements in new data-driven tools (e.g. artificial intelligence-based and mathematical morphology tools), significantly improving our analytical capabilities. Persisting in our investigation of these areas holds the potential for overcoming the current challenges in comprehending the evolution of large solar flares and CMEs, and for strengthening the model’s reliability. This pursuit, where fundamental and operational research meet, delivers encouraging results that could catalyze new mission launches and set the groundwork for more in-depth future studies. These efforts are further greatly enhanced by the advanced data expected from the next generation of state-of-the-art observational and forecasting tools.

Our proposed meeting session aims to comprehensively address crucial flare and CME-related research aspects, specifically focusing on their evolution and prediction. We welcome contributions that cover a wide range of research methodologies, from observational and modeling techniques (including data analysis and numerical approaches) to forecasting methods. This includes the utilization of statistical models, as well as the latest advancements in machine learning and artificial intelligence tools, to enhance our predictive capabilities and validation techniques.


Simone Chierichini (University of Sheffield)
Ronish Mugatwala (University of Sheffield)
Dr Marianna Korsos (University of Sheffield)


Session 1: Friday 19th July, 09:00 – 11:00

Session 1: Friday 19th July, 14:00 – 16:00