Correcting a coarse-grid climate model in multiple climates by machine learning from global 25-km resolution simulations

Spencer Koncius Clark, Noah Brenowitz, Brian Henn, Anna Kwa, Jeremy McGibbon, W. A. Perkins, Oliver Watt‐Meyer, Christopher S. Bretherton, Lucas Harris

Preprint · 02 June 2022 · Allen Institute for AI (Ai2, ACE), NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)

Paper

In one sentence. Machine-learned corrective tendencies from nudged 25 km runs improve land precipitation pattern errors by 17-30% in a coarse FV3GFS across four climates.

Abstract

Bretherton et al. (2022, https://doi.org/10.1029/2021MS002794) demonstrated a successful approach for using machine learning (ML) to help a coarse-resolution global atmosphere model with real geography (a ~200 km version of NOAA’s FV3GFS) evolve more like a fine-resolution model. This study extends that work for application in multiple climates and multi-year ML-corrected simulations. Here four fine-resolution (~25 km) two-year reference simulations are run using FV3GFS with climatological sea surface temperatures perturbed uniformly by -4 K, 0 K, +4 K, and +8 K. A dataset of state-dependent corrective tendencies is then derived through nudging the ~200 km model to the coarsened state of the fine-resolution simulations in each climate. Along with the surface radiative fluxes, the nudging tendencies of temperature and specific humidity are machine-learned as functions of the column state. ML predictions for the fluxes and corrective tendencies are applied in 5.25 year ~200 km resolution simulations in each climate, and improve the spatial pattern errors of land precipitation by 17% to 30% and land surface temperature by 20% to 23% across the four climates. The ML has a neutral impact on the pattern error of oceanic precipitation.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.