Producing realistic climate data with GANs

Abstract. This paper investigates the potential of a Wasserstein Generative Adversarial Networks to produce realistic weather situations when trained from the climate of a general circulation model (GCM). To do so, a convolutional neural network architecture is proposed for the generator and trained on a synthetic climate database, computed using a simple 3 dimensional climate model: PLASIM. The generator transforms a latent space , defined by a 64 dimensional Gaussian distribution, into spatially defined anomalies on the same output grid as PLASIM. The analysis of the statistics in the leading empirical orthogonal functions shows that the generator is able to reproduce many aspects of the multivariate distribution of the synthetic climate. Moreover, generated states reproduce the leading geostrophic balance present in the atmosphere. The ability to represent the climate state in a compact, dense and potentially nonlinear latent space opens new perspectives in the analysis and the handling of the climate. This contribution discusses the exploration of the extremes close to a given state and how to connect two realistic weather situations with this approach.

[1]  O. Pannekoucke,et al.  From the Kalman Filter to the Particle Filter: A Geometrical Perspective of the Curse of Dimensionality , 2016 .

[2]  Joachim Denzler,et al.  Predicting Landscapes as Seen from Space from Environmental Conditions , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Jie Chen,et al.  Evaluation of a weather generator-based method for statistically downscaling non-stationary climate scenarios for impact assessment at a point scale , 2012 .

[4]  D. Wilks,et al.  The weather generation game: a review of stochastic weather models , 1999 .

[5]  T. Davies.  Lateral boundary conditions for limited area models , 2014 .

[6]  Andrew C. Lorenc,et al.  The potential of the ensemble Kalman filter for NWP—a comparison with 4D‐Var , 2003 .

[7]  J. Dramsch,et al.  70 years of machine learning in geoscience in review , 2020, Advances in Geophysics.

[8]  G. Vallis.  Atmospheric and Oceanic Fluid Dynamics: Fundamentals and Large-Scale Circulation , 2017 .

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

[10]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[11]  Hannah M. Christensen,et al.  Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model , 2019, Journal of Advances in Modeling Earth Systems.

[12]  Joachim Denzler,et al.  Deep learning and process understanding for data-driven Earth system science , 2019, Nature.

[13]  Don Middleton,et al.  The abalone interpolation: a visual interpolation procedure for the calculation of cloud movement , 2002, Proceedings. XV Brazilian Symposium on Computer Graphics and Image Processing.

[14]  Liu Xinwu.  This is How the Discussion Started , 1981 .

[15]  Ahmed H. Elsheikh,et al.  Parametric generation of conditional geological realizations using generative neural networks , 2018, Computational Geosciences.

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

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

[18]  Lukas Gudmundsson,et al.  Emulating Earth system model temperatures with MESMER: from global mean temperature trajectories to grid-point-level realizations on land , 2018, Earth System Dynamics.

[19]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[20]  Fuqing Zhang,et al.  Review of the Ensemble Kalman Filter for Atmospheric Data Assimilation , 2016 .

[21]  S. Seneviratne,et al.  Emulating Earth System Model temperatures: from global mean temperature trajectories to grid-point level realizations on land , 2019 .

[22]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[23]  Jussi Leinonen,et al.  Reconstruction of Cloud Vertical Structure With a Generative Adversarial Network , 2019 .

[24]  Heiko Jansen,et al.  The Planet Simulator: Towards a user friendly model , 2005 .

[25]  Tom White,et al.  Sampling Generative Networks: Notes on a Few Effective Techniques , 2016, ArXiv.

[26]  Minh N. Do,et al.  Semantic Image Inpainting with Deep Generative Models , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[28]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).