Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models with Real-Geography Boundary Conditions

TL;DR

This study demonstrates that deep neural networks can effectively emulate cloud superparameterization in climate models with realistic geography, capturing key temporal and spatial features, and supporting hybrid modeling approaches.

Contribution

The paper introduces an optimized feed-forward neural network approach for emulating superparameterized convection in climate models with real-world geography, showing competitive skill and potential for hybrid climate modeling.

Findings

DNN explains over 70% of variance at 15-minute scale in the mid-to-upper troposphere.

Spectral analysis indicates skillful emulation of diurnal to synoptic scale signals.

Land-sea contrasts and vertical structure are well emulated, with some precipitation distortions.

Abstract

We explore the potential of feed-forward deep neural networks (DNNs) for emulating cloud superparameterization in realistic geography, using offline fits to data from the Super Parameterized Community Atmospheric Model. To identify the network architecture of greatest skill, we formally optimize hyperparameters using ~250 trials. Our DNN explains over 70 percent of the temporal variance at the 15-minute sampling scale throughout the mid-to-upper troposphere. Autocorrelation timescale analysis compared against DNN skill suggests the less good fit in the tropical, marine boundary layer is driven by neural network difficulty emulating fast, stochastic signals in convection. However, spectral analysis in the temporal domain indicates skillful emulation of signals on diurnal to synoptic scales. A close look at the diurnal cycle reveals correct emulation of land-sea contrasts and vertical structure in the heating and moistening fields, but some distortion of precipitation. Sensitivity tests targeting precipitation skill reveal complementary effects of adding positive constraints vs. hyperparameter tuning, motivating the use of both in the future. A first attempt to force an offline land model with DNN emulated atmospheric fields produces reassuring results further supporting neural network emulation viability in real-geography settings. Overall, the fit skill is competitive with recent attempts by sophisticated Residual and Convolutional Neural Network architectures trained on added information, including memory of past states. Our results confirm the parameterizability of superparameterized convection with continents through machine learning and we highlight advantages of casting this problem locally in space and time for accurate emulation and hopefully quick implementation of hybrid climate models.