Topics
Jonathan Citrin (Google DeepMind)
Henrik Eklund (ESA)
Opal Issan (UCSD)
Caitriona Jackman (DIAS)
Robert Jarolim (NCAR/HAO)
Sabrina Guastavino (Univ. of Genova)
George Miloshevich (KU Leuven)
Paul Wright (Univ. of Exeter)
The preliminary program can be downloaded
here.
The book of abstracts can be downloaded
here.
This Special Collection, inspired by the ML-Helio conference, highlights emerging advances in machine learning and data-driven methodologies that are transforming heliophysics research. Rapid developments in machine learning, deep learning, statistical inference, system identification, and information theory are opening new pathways to address long-standing scientific challenges and to realise greater value from the growing volume and diversity of heliospheric data.
The collection brings together a highly interdisciplinary research community—including experts in solar, heliospheric, magnetospheric, and aeronomy physics alongside computer scientists and data scientists—to advance methodological innovation and scientific discovery in heliophysics. Contributed works span a broad range of topics central to modern space science, including space weather forecasting, inverse estimation of physical parameters, automated event identification, feature detection and tracking, time-series analysis of dynamical systems, physics-informed machine learning, surrogate modelling, and uncertainty quantification.
Reflecting the integrative spirit of the ML-Helio conference, this Special Collection emphasises both fundamental advances and practical tools that drive progress across AGU journals such as JGR: Machine Learning and Computation, JGR: Space Physics, Space Weather, and Earth and Space Science. Together, these contributions chart the rapidly evolving landscape of machine learning in heliophysics and foster a collaborative community dedicated to accelerating scientific understanding of the Sun–Earth system.
Abigail Azari (U. Alberta) Jacob Bortnik (UCLA) Enrico Camporeale (CU/QMUL, chair) Yang Chen (U. Michigan) Veronique Delouille (ROB) Laura Hayes (DIAS) Farzad Kamalabadi (U. Illinois) Michael Kirk (NASA) Stefan Lotz (SANSA) Naoto Nishizuka (NICT, Japan) Pete Riley (Predictive Science Inc.) Simon Wing (APL, Johns Hopkins)
Arnaud Masson (ESA) Jan Reerink (ESA) Domenico Trotta (ESA)