This $309,517 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support the development and evaluation of artificial intelligence (AI) methods to analyze data from upcoming large-scale cosmological surveys, with a focus on weak gravitational lensing. The research team at the University of California, Berkeley will pursue two complementary AI approaches - generative learning using multiscale normalizing flows and discriminative learning with neural network-based compression architectures. The goal is to create optimal AI-powered tools to precisely and reliably extract cosmological information from real-world weak lensing data, advancing our understanding of the universe. The award also includes plans to engage a diverse group of students and incorporate the research lessons into physics and data science educational programs.
Generated 3/25/25, 4:25 AM