Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications. Foundation models (FMs), which are pre-trained on a large-scale datasets, form the basis for a variety of downstream tasks. These models, especially those based on transformers in vision and language, show exceptional potential for adapting to a wide range of downstream applications. In this paper, we provide our perspective on the criteria for designing an FM for heliophysics and associated challenges and applications using the Solar Dynamics Observatory (SDO) dataset. We believe that this is the first study to design an FM in the domain of heliophysics.
@article{arxiv.2410.10841,
title = {AI Foundation Model for Heliophysics: Applications, Design, and Implementation},
author = {Sujit Roy and Talwinder Singh and Marcus Freitag and Johannes Schmude and Rohit Lal and Dinesha Hegde and Soumya Ranjan and Amy Lin and Vishal Gaur and Etienne Eben Vos and Rinki Ghosal and Badri Narayana Patro and Berkay Aydin and Nikolai Pogorelov and Juan Bernabe Moreno and Manil Maskey and Rahul Ramachandran},
journal= {arXiv preprint arXiv:2410.10841},
year = {2024}
}