DOE OSTI · 1769746
Making Atmospheric Convective Parameterizations Obsolete with Machine Learning Emulation
Abstract
Parameterizations of moist convection in atmospheric models are notoriously problematic, and while global cloud resolving models (GCRM) are often touted as the ultimate solution, the computational cost is a considerable hurdle to overcome. Machine learning emulation of GCRMs for predictive modelling can leverage the DOE’s computational resource investments and allow widespread use of GCRMs such that traditional parameterizations become obsolete for most applications.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Hannah, Walter M., Pritchard, Michael S., Peters, John, Caldwell, Peter M., Tian, Yang, Choi, Youngsoo, Donahue, Aaron, Hillman, Benjamin. 2021-02-15. Making Atmospheric Convective Parameterizations Obsolete with Machine Learning Emulation. https://doi.org/10.2172/1769746. https://searchnasa.com/record/osti%3A1769746/making-atmospheric-convective-parameterizations-obsolete-with-machine-learning-emulation
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.