Abstract: I will review the broad range of work utilizing ML/AI for astronomy research at the University of Arizona and how our scientific questions push AI forward. I will discuss some of the limitations, including those encountered by our graduate student researchers and the critical need in our community for improved search and synthesis of the literature. I will discuss a possible path toward automated hypothesis generation through application of causal reasoning to structured and unstructured data extracted from scientific papers. 

Bio: Ann Zabludoff  has led studies across astronomy, astrophysics, and cosmology, including analyses of large observational datasets and theoretical simulations. She has worked to adapt astronomical instruments for new science. After obtaining S.B. degrees in Physics and in Mathematics from MIT, she received a Ph.D. in Astronomy from Harvard University. She was a Guggenheim Fellow, TEDx speaker, and the Caroline Herschel Distinguished Visitor at the Space Telescope Science Institute. She is a member of the UA College of Science Steering Committee for Data Science, Machine Learning, and AI and co-leads the Computation and Data Initiative of UA’s Theoretical Astrophysics Program. She is U.S. Participating Scientist on the Ultraviolet Transient Astronomy Satellite (ULTRASAT) science team. She has advised the National Science Foundation, NASA, the Department of Energy, and international research centers on science, policy, and prioritization.