Emulation of cloud microphysics in a climate model

Abstract

We present a machine learning based emulator of a microphysics scheme for condensation and precipitation processes (Zhao-Carr) used operationally in a global atmospheric forecast model (FV3GFS). Our tailored emulator architecture achieves high skill (≥94%) in predicting condensate and precipitation amounts and maintains low global-average bias (≤4%) for 1 year of continuous simulation when replacing the Fortran scheme. The stability and success of this emulator stems from key design decisions. By separating the emulation of condensation and precipitation processes, we can better enforce physical priors such as mass conservation and locality of condensation, and the vertical dependence of precipitation falling downward, using specific network architectures. An activity classifier for condensation imitates the discrete-continuous nature of the Fortran microphysics outputs (i.e., tendencies are identically zero where the scheme is inactive, and condensate is zero where clouds are fully evaporated). A temperature-scaled conditional loss function ensures accurate condensate adjustments for a high dynamic range of cloud types (e.g., cold, low-condensate cirrus clouds or warm, condensate-rich clouds). Despite excellent overall performance, the emulator exhibits some deficiencies in the uppermost model levels, leading to biases in the stratosphere. The emulator also has short episodic skill dropouts in isolated grid columns and is computationally slower than the original Fortran scheme. Nonetheless, our challenges and strategies should be applicable to the emulation of other microphysical schemes. More broadly, our work demonstrates that with suitable physically motivated architectural choices, ML techniques can accurately emulate complex human-designed parameterizations of fast physical processes central to weather and climate models.

Emulation of Cloud Microphysics in a Climate Model

“…The code and configurations used to produce training data, train ML models, and run FV3GFS simulations are available on Github (Perkins et al., 2023a, https://github.com/ai2cm/zc-emulation-manuscript) and archived on Zenodo (https://doi.org/10.5281/zenodo.7976184). The data and docker images to reproduce results with the code are available on Zenodo (Perkins et al., 2023b, https://doi.org/10.5281/zenodo.10637644).…”

“…The code and configurations used to produce training data, train ML models, and run FV3GFS simulations are available on Github (Perkins et al, 2023a,…”

A Machine Learning Parameterization of Clouds in a Coarse‐Resolution Climate Model for Unbiased Radiation

“…The rise of machine learning (ML, i.e., data-driven models) capabilities has fostered new approaches to improving parameterizations (Gentine et al, 2018). Examples include replacing computationally intensive physical parameterizations with ML emulation (Keller & Evans, 2019;Krasnopolsky et al, 2005Krasnopolsky et al, , 2010Lagerquist et al, 2021;O'Gorman & Dwyer, 2018;Perkins et al, 2023) and training ML against observations (Chen et al, 2023;McGibbon & Bretherton, 2019;Watt-Meyer et al, 2021) or more accurate and computationally intensive parameterizations (Chantry et al, 2021). ML parameterizations for coarse-grid models have been trained on coarsened (coarse-grained) outputs of fine-grid or super-parameterized reference simulations, for example, to predict the effect of the full physics parameterization (Brenowitz & Bretherton, 2019;Han et al, 2020;Rasp et al, 2018;Watt-Meyer et al, 2024;Yuval et al, 2021), or a column-wise correction to the coarse-grid model physics (Bretherton et al, 2022;Clark et al, 2022;Kwa et al, 2023).…”