Machine Learning and Mathematical Methods in Heliophysics

The NASA Postdoctoral Program offers unique research opportunities to highly-talented scientists to engage in ongoing NASA research projects at a NASA Center, NASA Headquarters, or at a NASA-affiliated research institute. These one- to three-year fellowships are competitive and are designed to advance NASA's missions in space science, Earth science, aeronautics, space operations, exploration systems, and astrobiology. This specific opportunity emphasizes the use of machine learning, AI, and advanced mathematical methods to expand the discovery potential of heliophysics mission data, theoretical models, and simulations. Heliophysics has a vast wealth of data, sampling a wide range of domains, such as the solar interior, corona, heliosphere, magnetosphere, ionosphere, upper atmosphere. Modern methods in data science have the potential to access new, exciting results that eluded classical analysis approaches. This opportunity focuses on using machine learning and advanced mathematical methods to reveal fundamental physical processes that govern heliophysical systems, and adaptation of methods to specifically target the underlying physics can help turn an improved correlation or forecast into deeper physical insight and understanding. Examples include deep learning, neural networks, data segmentation, high dimensionality, and advanced statistical/probabilistic methods.