The MOSAIICS team organized the second conference on machine learning and computer vision in heliophysics in Bulgaria, after the one in 2023. This hybrid (online and in person) interdisciplinary conference was held in Sofia between April 07-09, 2025. It focused on applications of Computer Vision and Machine / Deep Learning techniques to heliophysics research and forecasting frameworks, as well as on the integration of these techniques into modeling efforts of solar and heliospheric phenomena. Topics included Computer Vision and Machine Learning applications in heliophysics, Computer Vision and Machine Learning techniques, explainable Machine Learning and Physics-informed networks, and tools for CV and ML (based on Python, OpenCV, scikit-learn, TF/Pytorch, etc.).
The scientific organizing committee included Jorge Amaya (ESA), Manolis Georgoulis (Applied Physics Laboratory, Johns Hopkins University, USA), Robert Jarolim (High Altitude Observatory, USA), Shane Maloney (Dublin Institute for Advanced Studies, Ireland), Michele Piana (Università di Genova, Italy), Pietro Zucca (ASTRON, Netherlands). Over 60 scientists from 13 countries and over 30 institutions attended the highly successful conference in person and online, a large majority of whom were young researchers. The conference program, abstracts, and the list of participants are available on the conference website, https://mch25.astro.bas.bg.
