Dr. Christopher Bretherton | Improving Climate Models Using Corrective Machine Learning

FULL TITLE: Improving Climate Models Using Corrective Machine Learning vs. Other Emulation Approaches

Abstract:
AI2, with GFDL, has developed a corrective machine learning (ML) methodology to improve weather forecast skill and reduce climate biases in a computationally efficient coarse-grid climate model. The corrective ML is trained by nudging the 3D temperature, humidity and wind fields forecast by the coarse-grid model to a time-dependent global reference and learning the ‘nudging tendencies’ as a function of the column state of the model. The reference can be a reanalysis (for present-climate simulation) or a finer-grid version of the same model that may be more trustworthy across a range of climates. The ML is interpreted as a correction to the combined physics parameterizations of the coarse-grid model. We trained the ML on global 25 km simulations in multiple climates, and separately on a year-long 3 km simulation, and applied it in 200 km coarse-grid simulations. The ML reduced annual-mean land temperature and precipitation pattern biases by up to 50% and enhanced weather forecast skill. We compare strengths and weaknesses of this method vs. other strategies for emulating reference climate models, including another hybrid approach using reservoir computing, and full model emulation.

Biosketch:
Chris Bretherton directs a climate modeling group at AI2 in Seattle which uses machine learning trained on global storm-resolving model output and observational data to improve climate model simulations. He is an Emeritus Professor of the Atmospheric Science and Applied Mathematics Departments at the University of Washington, where for 35 years he studied cloud formation and turbulence and improved their simulation in atmospheric models. He is an American Meteorological Society Charney Award winner, IPCC author, AMS and AGU Fellow, and a member of the National Academy of Sciences.

[kirkg]

Chris lived in Baltimore & briefly (1971/1972) went to Pimlico Jr. High. He was brilliant then. I googled him strictly because I remembered him & figured he'd be a big deal as an adult.

[damien]

is it really worth the effort for the climate? I was looking at the IPCC AR5 published 9 years ago, and not one of their models was remotely close to forecast the last 8 years (global land & ocean temperatures have been flat since 2015)

[scomo]

In October of 2022 on their website NOAA published their predictions for the upcoming winter. They claimed that southern CA and the SW in general would continue to be influenced by La Niña and as such locales woild experience warmer and drier conditions than normal. Whoa! As we all now know, were they ever wrong! CA was much cooler than as n normal and broke the all time record for snowfall in the Sierra. The mountains east of LA were paralyzed by 7-8 ft of snow in early Feb. LA received far more rain in Feb and Narch than it does in a year. AZ was much cooler and wetter than usual with floods in Sedona and Phoenix. Laughlin NV had a major flood.
All models have the biases of the modeler naked in. They’re worthless.