Using Deep Neural Networks as Cost‐Effective Surrogate Models for Super‐Parameterized E3SM Radiative Transfer

Deep neural networks (DNNs) are implemented in Super‐Parameterized Energy Exascale Earth System Model (SP‐E3SM) to imitate the shortwave and longwave radiative transfer calculations. These DNNs were able to emulate the radiation parameters with an accuracy of 90–95% at a cost of 8–10 times cheaper than the original radiation parameterization. A comparison of time‐averaged radiative fluxes and the prognostic variables manifested qualitative and quantitative similarity between the DNN emulation and the original parameterization. It has also been found that the differences between the DNN emulation and the original parameterization are comparable to the internal variability of the original parameterization. Although the DNNs developed in this investigation emulate the radiation parameters for a specific set of initial conditions, the results justify the need of further research to generalize the use of DNNs for the emulations of full model radiation and other parameterization for seasonal predictions and climate simulations.

[1]  Sebastian Scher,et al.  Toward Data‐Driven Weather and Climate Forecasting: Approximating a Simple General Circulation Model With Deep Learning , 2018, Geophysical Research Letters.

[2]  Sebastian Scher,et al.  Predicting weather forecast uncertainty with machine learning , 2018, Quarterly Journal of the Royal Meteorological Society.

[3]  Pierre Gentine,et al.  Could Machine Learning Break the Convection Parameterization Deadlock? , 2018, Geophysical Research Letters.

[4]  Pierre Gentine,et al.  Deep learning to represent subgrid processes in climate models , 2018, Proceedings of the National Academy of Sciences.

[5]  Stephan Rasp,et al.  Neural networks for post-processing ensemble weather forecasts , 2018, Monthly Weather Review.

[6]  Donald D. Lucas,et al.  Machine Learning Predictions of a Multiresolution Climate Model Ensemble , 2018 .

[7]  D. Bader.  Energy Exascale Earth System Model (E3SM) Project Strategy , 2017 .

[8]  David A. Randall,et al.  Robust effects of cloud superparameterization on simulated daily rainfall intensity statistics across multiple versions of the Community Earth System Model , 2016 .

[9]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[10]  Richard C. J. Somerville,et al.  Robustness and sensitivities of central U.S. summer convection in the super‐parameterized CAM: Multi‐model intercomparison with a new regional EOF index , 2013 .

[11]  Stephen J. Lord,et al.  Accurate and Fast Neural Network Emulations of Model Radiation for the NCEP Coupled Climate Forecast System: Climate Simulations and Seasonal Predictions* , 2010 .

[12]  Jean-Claude Thelen,et al.  Two fast radiative transfer methods to improve the temporal sampling of clouds in numerical weather prediction and climate models , 2009 .

[13]  J. Morcrette,et al.  Impact of a New Radiation Package, McRad, in the ECMWF Integrated Forecasting System , 2008 .

[14]  George Mozdzynski,et al.  A Reduced Radiation Grid for the ECMWF Integrated Forecasting System , 2008 .

[15]  Vladimir M. Krasnopolsky,et al.  Decadal Climate Simulations Using Accurate and Fast Neural Network Emulation of Full, Longwave and Shortwave, Radiation* , 2008 .

[16]  Reto Knutti,et al.  Constraints on Model Response to Greenhouse Gas Forcing and the Role of Subgrid-Scale Processes , 2008 .

[17]  Vladimir M. Krasnopolsky,et al.  Neural network approach for robust and fast calculation of physical processes in numerical environmental models: Compound parameterization with a quality control of larger errors , 2008, Neural Networks.

[18]  David A. Randall,et al.  Evaluation of the Simulated Interannual and Subseasonal Variability in an AMIP-Style Simulation Using the CSU Multiscale Modeling Framework , 2008 .

[19]  Vladimir M. Krasnopolsky,et al.  Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather prediction , 2006, Neural Networks.

[20]  Vladimir M. Krasnopolsky,et al.  A new synergetic paradigm in environmental numerical modeling: Hybrid models combining deterministic and machine learning components , 2006 .

[21]  D. Randall,et al.  Simulations of the Atmospheric General Circulation Using a Cloud-Resolving Model as a Superparameterization of Physical Processes , 2005 .

[22]  D. Chalikov,et al.  New Approach to Calculation of Atmospheric Model Physics: Accurate and Fast Neural Network Emulation of Longwave Radiation in a Climate Model , 2005 .

[23]  Shepard A. Clough,et al.  Atmospheric radiative transfer modeling: a summary of the AER codes , 2005 .

[24]  Shepard A. Clough,et al.  The QME AERI LBLRTM: A Closure Experiment for Downwelling High Spectral Resolution Infrared Radiance , 2004 .

[25]  Michael Buchhold,et al.  The Operational Global Icosahedral-Hexagonal Gridpoint Model GME: Description and High-Resolution Tests , 2002 .

[26]  Jean-Jacques Morcrette,et al.  On the Effects of the Temporal and Spatial Sampling of Radiation Fields on the ECMWF Forecasts and Analyses , 2000 .

[27]  Alain Chedin,et al.  A Neural Network Approach for a Fast and Accurate Computation of a Longwave Radiative Budget , 1998 .

[28]  A. Staniforth,et al.  The Operational CMC–MRB Global Environmental Multiscale (GEM) Model. Part I: Design Considerations and Formulation , 1998 .

[29]  A. Staniforth,et al.  The Operational CMC–MRB Global Environmental Multiscale (GEM) Model. Part II: Results , 1998 .

[30]  Shepard A. Clough,et al.  Accelerated monochromatic radiative transfer for scattering atmospheres: Application of a new model to spectral , 1997 .

[31]  E. Mlawer,et al.  Radiative transfer for inhomogeneous atmospheres: RRTM, a validated correlated-k model for the longwave , 1997 .

[32]  A. Lacis,et al.  A description of the correlated k distribution method for modeling nongray gaseous absorption, thermal emission, and multiple scattering in vertically inhomogeneous atmospheres , 1991 .