Deep Learning Applications for Space Science

We present some example applications of deep learning to a number of challenging problems encountered in Heliophysics. They include (1) spectropolarimetric inversions for measuring the magnetic field on the solar surface (e.g. using data from Hinode and the Solar Dynamics Observatory), and (2) thermal mapping of the Sun's corona (i.e. differential emission measure inversions) using a deep neural network to solve a compressed sensing problem. We argue that applying machine learning to Heliophysics data not only accelerates scientific discovery from existing assets, it also opens up novel concepts for deep space missions for solar and space weather monitoring. Some of the work in this presentation was made possible by NASA's Frontier Development Lab, a public-private partnership between the agency and industry partners (including the SETI Institute, NVIDIA, IBM, Intel, kx & Lockheed Martin), whose mission is to use artificial intelligence to tackle problems related to planetary defense and heliophysics.