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

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 a network architecture of greatest skill, we formally optimize its 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. The spatial relationship between DNN skill and autocorrelation timescale shows performance is weakest in the tropical, marine boundary layer. 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 emulation. 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 suggesting 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 in the presence of 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.