The Massachusetts Institute of Technology (MIT) received a $1.2 million project grant award from the National Science Foundation Office of Advanced Cyberinfrastructure to support research activities under the Computer and Information Science and Engineering federal grant program (CFDA 47.070).
The award will fund a collaborative research project between Aug 1, 2021 and Jul 31, 2025 to develop frameworks that converge Bayesian inverse methods and scientific machine learning in Earth system models through universal differentiable programming. This work aims to advance the development and use of research cyberinfrastructure to enable and accelerate discovery and innovation in computing, communications, and information science and engineering, as supported by the goals of the CFDA 47.070 program. The grant will support MIT investigator-initiated efforts to apply machine learning and optimization techniques to complex Earth system modeling challenges over a four-year period using a differentiated programming approach.
Generated 1/7/24, 5:33 AM