Hybrid physics-ML & parameterization★ Highlight

Correcting Weather and Climate Models by Machine Learning Nudged Historical Simulations

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

Geophysical Research Letters · 15 July 2021 · Allen Institute for AI (Ai2, ACE), NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), Princeton University, University of Washington

Paper PDF

Why it matters. Random forest learns nudging tendencies to correct FV3GFS biases, stable in year-long runs and cutting precipitation error by 20%; important for ML bias correction.

In one sentence. A random forest learns nudging tendencies and is coupled to FV3GFS, reducing 500 hPa height forecast error and annual-mean precipitation RMSE by about 20% in year-long runs.

Abstract

Abstract Due to limited resolution and inaccurate physical parameterizations, weather and climate models consistently develop biases compared to the observed atmosphere. Using the FV3GFS model at coarse resolution, we propose a method of machine learning corrective tendencies from a hindcast simulation nudged toward observational analysis. We show that a random forest can predict the nudging tendencies from this hindcast simulation with moderate skill using only the model state as input. This random forest is then coupled to FV3GFS, adding corrective tendencies of temperature, specific humidity and horizontal winds at each timestep. The coupled model shows no signs of instability in year‐long simulations and has significant reductions in short‐term forecast error for 500 hPa height, surface pressure and near‐surface temperature. Furthermore, the root mean square error of the annual‐mean precipitation is reduced by about 20%. Biases of other variables remain similar or in some cases, like upper‐atmospheric temperature, increase in the year‐long simulations.

Labels

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