Machine Learning the Warm Rain Process. (16th February 2021)

• Record Type: Journal Article
• Authors: Gettelman, A.; Gagne, D. J.; Chen, C.‐C.; Christensen, M. W.; Lebo, Z. J.; Morrison, H.; Gantos, G.
• Is Part Of: Journal of advances in modeling earth systems. Volume 13:Number 2(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-02-16
• Subjects: clouds -- machine learning -- microphysics; Geological modeling -- Periodicals; Climatology -- Periodicals; Geochemical modeling -- Periodicals; 551.5011
• DOI: 10.1029/2020MS002268
• Languages: English
• ISSNs: 1942-2466

Abstract

Abstract: Clouds are critical for weather and climate prediction. The multiple scales of cloud processes make simulation difficult. Often models and measurements are used to develop empirical relationships for large‐scale models to be computationally efficient. Machine learning provides another potential tool to improve our empirical parameterizations of clouds. To explore these opportunities, we replace the warm rain formation process in a General Circulation Model (GCM) with a detailed treatment from a bin microphysical model that causes a 400% slowdown in the GCM. We analyze the changes in climate that result from the use of the bin microphysical calculation and find improvements in the rain onset and frequency of light rain compared to high resolution process models and observations. We also find a resulting change in the cloud feedback response of the model to warming, which will significantly impact the climate sensitivity. We then replace the bin microphysical model with several neural networks designed to emulate the autoconversion and accretion rates produced by the bin microphysical model. The neural networks are organized into two stages: the first stage identifies where tendencies will be nonzero (and the sign of the tendency), and the second stage predicts the magnitude of the autoconversion and accretion rates. We describe the risks of overfitting, extrapolation, and linearization by using perfect model experiments with and without the emulator. We can recover the solutions with the emulators in almost all respects, and get simulations that perform as the detailed model, but with the computational cost of the control simulation. Plain Language Summary: Cloud processes are perhaps the most critical and uncertain processes for weather and climate prediction. The complex nature of clouds and their variation at small spacial scales makes simulation of clouds very challenging. There exist many observations and detailed simulations of clouds that are used to develop and evaluate larger‐scale models. Many times these models and measurements are used to develop empirical relationships for large‐scale models to be computationally efficient. Machine learning provides another potential tool to improve our empirical parameterizations of clouds. We replace the warm rain formation process in an earth system model with an emulator. The emulator consists of multiple neural networks that predict whether specific tendencies will be nonzero and the magnitude of the nonzero tendencies. We describe the opportunity (massive speed up of cloud process calculations) and the risks of overfitting, extrapolation and linearization of a nonlinear problem by using perfect model experiments with and without the emulator. Key Points: A stochastic bin model of warm rain formation is added to a General Circulation Model at high computational cost Key warm rain metrics are improved, including precipitation onset and frequency Neural networks can efficiently replicate the results of a stochastic bin model rain scheme with low computational cost