The representation of nonlinear sub-grid processes, especially clouds, has been a major source of uncertainty in climate models for decades. Cloud-resolving models better represent many of these processes and can now be run globally but only for short-term simulations of at most a few years because of computational limitations. Here we demonstrate that deep learning can be used to capture many advantages of cloud-resolving modeling at a fraction of the computational cost. We train a deep neural network to represent all atmospheric sub-grid processes in a climate model by learning from a multi-scale model in which convection is treated explicitly. The trained neural network then replaces the traditional sub-grid parameterizations in a global general circulation model in which it freely interacts with the resolved dynamics and the surface-flux scheme. The prognostic multi-year simulations are stable and closely reproduce not only the mean climate of the cloud-resolving simulation but also key aspects of variability, including precipitation extremes and the equatorial wave spectrum. Furthermore, the neural network approximately conserves energy despite not being explicitly instructed to. Finally, we show that the neural network parameterization generalizes to new surface forcing patterns but struggles to cope with temperatures far outside its training manifold. Our results show the feasibility of using deep learning for climate model parameterization. In a broader context, we anticipate that data-driven Earth System Model development could play a key role in reducing climate prediction uncertainty in the coming decade.
Paraformer: Parameterization of Sub-grid Scale Processes Using Transformers
Northeastern University（东北大学）；Microsoft Corporation（微软公司）；The Institute for Experiential AI（体验式人工智能研究所）；Roux Institute（鲁克斯研究所）；Zeus AI（宙斯人工智能公司）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
University of Lausanne（洛桑大学）；Columbia University（哥伦比亚大学）；Massachusetts Institute of Technology（麻省理工学院）；University of California, Irvine（加利福尼亚大学尔湾分校）；Google Research（谷歌研究院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；NVIDIA（英伟达）
Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
National Center for Atmospheric Research（美国国家大气研究中心）；University of Colorado Boulder（科罗拉多大学博尔德分校）；University of Victoria（维多利亚大学）；University of Oxford（牛津大学）
Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks
Western Washington University（西华盛顿大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）；Indiana University（印第安纳大学）；Joint Global Change Research Institute（联合全球变化研究所）；Computer Science Department, Western Washington University（西华盛顿大学计算机科学系）；Computing & Analytics Division, Pacific Northwest National Laboratory（太平洋西北国家实验室计算与分析部）；Earth and Atmospheric Sciences Department, Indiana University（印第安纳大学地球与大气科学系）
