Abstract
Coarse-grid weather and climate models rely particularly on
parameterizations of cloud fields, and coarse-grained cloud fields from a
fine-grid reference model are a natural target for a machine-learned
parameterization. We machine-learn the coarsened-fine cloud properties as
a function of coarse-grid model state in each grid cell of NOAA's
FV3GFS global atmosphere model with 200 km grid spacing, trained using a
3-km fine-grid reference simulation with a modified version of FV3GFS. The
ML outputs are coarsened-fine fractional cloud cover and liquid and ice
cloud condensate mixing ratios, and the inputs are coarse model
temperature, pressure, relative humidity, and ice cloud condensate. The
predicted fields are skillful and unbiased, but somewhat under-dispersed,
resulting in too many partially-cloudy model columns. When the predicted
fields are applied diagnostically (offline) in FV3GFS's radiation
scheme, they lead to small biases in global-mean top-of-atmosphere (TOA)
and surface radiative fluxes. An unbiased global-mean TOA net radiative
flux is obtained by setting to zero any predicted cloud with grid-cell
mean cloud fraction less than a threshold of 6.5%; this does not
significantly degrade the ML prediction of cloud properties. The
diagnostic, ML-derived radiative fluxes are far more accurate than those
obtained with the existing cloud parameterization in the nudged
coarse-grid model, as they leverage the accuracy of the fine-grid
reference simulation's cloud properties.This dataset provides the
coarsened fine-grid model outputs needed to run the nudged coarse climate
model, including running with prescribed coarsened fine-grid cloud fields
and to train the ML model that predicts coarsened-fine cloud fields as
functions of nudged coarse model state.