DeepClimGAN: A High-Resolution Climate Data Generator

Earth system models (ESMs), which simulate the physics and chemistry of the global atmosphere, land, and ocean, are often used to generate future projections of climate change scenarios. These models are far too computationally intensive to run repeatedly, but limited sets of runs are insufficient for some important applications, like adequately sampling distribution tails to characterize extreme events. As a compromise, emulators are substantially less expensive but may not have all of the complexity of an ESM. Here we demonstrate the use of a conditional generative adversarial network (GAN) to act as an ESM emulator. In doing so, we gain the ability to produce daily weather data that is consistent with what ESM might output over any chosen scenario. In particular, the GAN is aimed at representing a joint probability distribution over space, time, and climate variables, enabling the study of correlated extreme events, such as floods, droughts, or heatwaves.

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

[2]  Andrew Stuart,et al.  Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High‐Resolution Simulations , 2017, 1709.00037.

[3]  Alexander J. Smola,et al.  Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy , 2016, ICLR.

[4]  H. Hasumi,et al.  Improved Climate Simulation by MIROC5: Mean States, Variability, and Climate Sensitivity , 2010, Journal of Climate.

[5]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[8]  Dan Lu,et al.  Efficient surrogate modeling methods for large-scale Earth system models based on machine learning techniques , 2019, Geoscientific Model Development.

[9]  Antonio Torralba,et al.  Generating Videos with Scene Dynamics , 2016, NIPS.

[10]  Arthur Gretton,et al.  Interpretable Distribution Features with Maximum Testing Power , 2016, NIPS.

[11]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[12]  Karl E. Taylor,et al.  An overview of CMIP5 and the experiment design , 2012 .

[13]  Ko Koizumi.  An Objective Method to Modify Numerical Model Forecasts with Newly Given Weather Data Using an Artificial Neural Network , 1999 .

[14]  Karthik Kashinath,et al.  Enforcing statistical constraints in generative adversarial networks for modeling chaotic dynamical systems , 2019, J. Comput. Phys..

[15]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[16]  Charles A. Doswell,et al.  Precipitation Forecasting Using a Neural Network , 1999 .

[17]  B. Kravitz,et al.  Technical note: Deep learning for creating surrogate models of precipitation in Earth system models , 2019, Atmospheric Chemistry and Physics.

[18]  Peter Bauer,et al.  Challenges and design choices for global weather and climate models based on machine learning , 2018, Geoscientific Model Development.

[19]  Noah D. Brenowitz,et al.  Prognostic Validation of a Neural Network Unified Physics Parameterization , 2018, Geophysical Research Letters.