CEDAR email: Machine learning and data science session at ESWW 2026

[Wing, Simon]

Dear Colleagues,
We invite you to contribute a Machine learning and data science session at European Space Weather Week 2026 (ESWW 2026) scheduled for November 2-6, 2026 in Florence, Italy.  The session title and abstract are given below. The abstract submission deadline is May 15, 2026.

Abstract submission Link:  https://esww.aeronomie.be/calls/call-for-abstracts
OTH3 – Machine Learning and Data Science for Geospace and Space Weather

Conveners: Georgios BALASIS; Simon WING; Yuri SHPRITS; Jorge AMAYA

Description: The world is in the midst of an artificial intelligence (AI) and machine learning (ML) revolution. Given its widespread impact, it is not surprising to see an explosion in the applications of ML in academic research, including geospace and space weather research. Over the last few decades, both satellite missions and ground-based networks, along with their associated instruments, are yielding exponentially increasing volumes of data. Concurrently, the growth in computational power is enabling simulations to produce similarly vast datasets. These extensive observational and simulation outputs present significant challenges to conventional data analysis methodologies. Machine learning is emerging as a valuable tool for facilitating the analysis, classification, characterization, forecasting, and discovery processes within large datasets. Likewise, advanced data and complex system sciences provide robust frameworks for analyzing, mining, and elucidating both linear and nonlinear relationships as well as causal inferences within large complex data sets. Machine learning has also constantly improving the performance of operational space weather models, and thus, the predictions of hazardous space weather effects for the space and ground infrastructures. This session welcomes submissions in the following areas related to Machine Learning integrated into Space Weather research: solar flare prediction, geomagnetic storm forecasts, radiation belt modeling, CME propagation, MIT coupling and its effects etc. The session also aspires to highlight the importance to develop data standards and in particular metadata standards and prepare AI ready data compliant with FAIR principles.


Simon Wing
240-228-8075
simon.wing at jhuapl.edu



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.ucar.edu/pipermail/cedar_email/attachments/20260512/ebe3e2e6/attachment-0001.htm>