Modeling Cloud Reflectance Fields using Conditional Generative Adversarial Networks

We introduce a conditional Generative Adversarial Network (cGAN) approach to generate cloud reflectance fields (CRFs) conditioned on large scale meteorological variables such as sea surface temperature and relative humidity. We show that our trained model can generate realistic CRFs from the corresponding meteorological observations, which represents a step towards a data-driven framework for stochastic cloud parameterization.

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

[2]  A. Arakawa.  The Cumulus Parameterization Problem: Past, Present, and Future , 2004 .

[3]  Ali Borji,et al.  Pros and Cons of GAN Evaluation Measures , 2018, Comput. Vis. Image Underst..

[4]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Jan Kautz,et al.  High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Jae Hyun Lim,et al.  Geometric GAN , 2017, ArXiv.

[7]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[8]  Qiang Fu,et al.  Mean radiative energy balance and vertical mass fluxes in the equatorial upper troposphere and lower stratosphere , 2005 .

[9]  P. O'Gorman,et al.  Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events , 2018, Journal of Advances in Modeling Earth Systems.

[10]  B. Barkstrom,et al.  Cloud-Radiative Forcing and Climate: Results from the Earth Radiation Budget Experiment , 1989, Science.

[11]  C. Bretherton.  Insights into low-latitude cloud feedbacks from high-resolution models , 2015, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

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

[13]  Bin Zhao,et al.  The Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). , 2017, Journal of climate.

[14]  Robert F. Cahalan,et al.  Energy Balance Climate Models , 2017 .

[15]  Gauthier Gidel,et al.  A Variational Inequality Perspective on Generative Adversarial Networks , 2018, ICLR.

[16]  A. P. Siebesma,et al.  Climate goals and computing the future of clouds , 2017 .

[17]  Vincent Dumoulin,et al.  Deconvolution and Checkerboard Artifacts , 2016 .

[18]  Richard Simon,et al.  Bias in error estimation when using cross-validation for model selection , 2006, BMC Bioinformatics.

[19]  Steven Platnick,et al.  The MODIS Cloud Optical and Microphysical Products: Collection 6 Updates and Examples From Terra and Aqua , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[20]  D. Hartmann,et al.  The Effect of Cloud Type on Earth's Energy Balance: Global Analysis , 1992 .

[21]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).