Over the past 50 years, a variety of instruments have obtained images of the Sun’s magnetic field (magnetograms) to study its origin and evolution. While improvements in instrumentation have led to breakthroughs in our understanding of physical phenomena, differences between subsequent instruments such as resolution, noise, and saturation levels all introduce inhomogeneities into long-term data sets. This poses a significant issue for research applications that require high-resolution and homogeneous data spanning time frames longer than the lifetime of a single instrument.
 Jungbluth, A., Gitiaux, X., Maloney, S., Shneider, C., Wright, P. J., et al, 2019. Single-Frame Super-Resolution of Solar Magnetograms: Investigating Physics-Based Metrics & Losses, in 33rd Neural Information Processing Systems (NeurIPS) workshop on Machine Learning in Physical Sciences, Vancouver, Canada, 2019
 Gitiaux, X., Maloney, S., Jungbluth, A., Shneider, C., Wright, P. J., et al, 2019. Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties, in 33rd Neural Information Processing Systems (NeurIPS) workshop on Bayesian Deep Learning, Vancouver, Canada, 2019
bold denotes researchers advised/mentored
Google Cloud recently developed a microsite ([cloud.withgoogle.com/intel](https://cloud.withgoogle.com/intel/)), and produced videos about our work at the Frontier Development Lab (FDL). Check out the video below!