The University of Texas at Austin received a $1,278,970 project grant award from the National Science Foundation Office of Advanced Cyberinfrastructure to support research titled "COLLABORATIVE RESEARCH: FRAMEWORKS: CONVERGENCE OF BAYESIAN INVERSE METHODS AND SCIENTIFIC MACHINE LEARNING IN EARTH SYSTEM MODELS THROUGH UNIVERSAL DIFFERENTIABLE PROGRAMMING" from August 1, 2021 through July 31, 2025.
The grant is part of the NSF's Computer and Information Science and Engineering program (CFDA #47.070), which supports investigator-initiated research and education in computing, communications, and information science and engineering. The University will conduct research to advance the development and use of cyberinfrastructure to enable and accelerate discovery and innovation in earth system modeling. This includes work on frameworks to converge Bayesian inverse methods and scientific machine learning to parameterize earth system models through universal differentiable programming. The award will fund this research effort over a four-year period ending in July 2025.