Stable Machine-Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection-Permitting Simulations
Zeyuan Hu, Akshay Subramaniam, Zhiming Kuang, Jerry Lin, Sungduk Yu, Walter M. Hannah, Noah D. Brenowitz, Josh Romero, Michael S. Pritchard
备注：
37 pages, 12 figures in the main text, 3 figures in appendix. This version is an update from the previous version 3 to include additional evaluation analysis
Modern climate projections often suffer from inadequate spatial and temporal resolution due to computational limitations, resulting in inaccurate representations of sub-grid processes. A promising technique to address this is the Multiscale Modeling Framework (MMF), which embeds a kilometer-resolution cloud-resolving model within each atmospheric column of a host climate model to replace traditional convection and cloud parameterizations. Machine learning (ML) offers a unique opportunity to make MMF more accessible by emulating the embedded cloud-resolving model and reducing its substantial computational cost. Although many studies have demonstrated proof-of-concept success of achieving stable hybrid simulations, it remains a challenge to achieve near operational-level success with real geography and comprehensive variable emulation that includes, for example, explicit cloud condensate coupling. In this study, we present a stable hybrid model capable of integrating for at least 5 years with near operational-level complexity, including coarse-grid geography, seasonality, explicit cloud condensate and wind predictions, and land coupling. Our model demonstrates skillful online performance, achieving a 5-year zonal mean tropospheric temperature bias within 2K, water vapor bias within 1 g/kg, and a precipitation RMSE of 0.96 mm/day. Key factors contributing to our online performance include an expressive U-Net architecture and physical thermodynamic constraints for microphysics. With microphysical constraints mitigating unrealistic cloud formation, our work is the first to demonstrate realistic multi-year cloud condensate climatology under the MMF framework. Despite these advances, online diagnostics reveal persistent biases in certain regions, highlighting the need for innovative strategies to further optimize online performance.
Use of neural networks for stable, accurate and physically consistent parameterization of subgrid atmospheric processes with good performance at reduced precision
Cloud Feedback on Earth's Long-term Climate Simulated by a Near-global Cloud-permitting Model
随着时间的推移，太阳会变得更亮，但地球的气候在其长期历史中大致适合生命;对于早期地球，这被称为微弱的年轻太阳问题（FYSP）。除了碳酸盐-硅酸盐反馈外，最近的研究表明，长期的云反馈可能部分解决FYSP。然而，他们使用的大气环流模型不能明确地解决对流和云。本研究使用一个没有积云对流参数化的近全球云允许模式重新调查云。我们的研究结果证实，一个稳定的短波云反馈确实存在，它的大小是$\approx$ 6 W m $^{-2}$或14%的能量所需的抵消20%比今天暗的太阳，或$\approx$ 10 W m $^{-2}$或16%的30%暗的太阳。当太阳辐射增加，同时CO $_2$浓度降低时，低空云层增加，通过提高行星的云量来稳定气候，反之亦然。
From stable online coupling to decade-long climate simulations: A machine learning parameterization for cloud microphysics in ICON
Deutsches Zentrum für Luft- und Raumfahrt e.V.（德国航空航天中心）；University of Oxford（牛津大学）；European Centre for Medium-Range Weather Forecasts（欧洲中期天气预报中心）；University of Bremen（不来梅大学）
Impact of Data-Driven Eddy Parameterization on Climate State in an Idealized Coupled CESM Model
Courant Institute School of Mathematics, Computing, and Data Science, New York University（纽约大学柯朗数学科学研究所）；Atmospheric and Oceanic Sciences Program, Princeton University（普林斯顿大学大气与海洋科学项目）
Beyond the Training Data: Confidence-Guided Mixing of Parameterizations in a Hybrid AI-Climate Model
Deutsches Zentrum für Luft- und Raumfahrt（德国航空航天中心）；Faculty of Geosciences and Environment, University of Lausanne（洛桑大学地球科学与环境学院）；Expertise Center for Climate Extremes, University of Lausanne（洛桑大学气候极端研究中心）；University of Bremen, Institute of Environmental Physics (IUP)（不来梅大学环境物理研究所）
Data Imbalance, Uncertainty Quantification, and Generalization via Transfer Learning in Data-driven Parameterizations: Lessons from the Emulation of Gravity Wave Momentum Transport in WACCM
Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles
Expertise Center for Climate Extremes, University of Lausanne（洛桑大学气候极端事件专业中心）；NVIDIA Research（英伟达研究院）；Department of Biomedical Data Science, Stanford University School of Medicine（斯坦福大学医学院生物医学数据科学系）；Department of Earth System Sciences, University of California at Irvine（加州大学欧文分校地球系统科学系）；Multimodal Cognitive AI, Intel Labs（英特尔实验室多模态认知人工智能部门）；Faculty of Geosciences and Environment, University of Lausanne（洛桑大学地球科学与环境学院）；Department of Statistics, University of California at Irvine（加州大学欧文分校统计系）；Department of Earth and Planetary Sciences, Harvard University（哈佛大学地球与行星科学系）；LEAP Science and Technology Center, School of Engineering and Applied Sciences, Climate School, Columbia University（哥伦比亚大学气候学院工程与应用科学学院LEAP科技中心）；Berkeley AI Research (BAIR), Department of Electrical Engineering and Computer Science, University of California at Berkeley（加州大学伯克利分校电气工程与计算机科学系伯克利人工智能研究中心）
Improved Precipitation Variability in the Community Atmosphere Model through Implementation of a Neural-Network Deep Convection Scheme
Columbia University（哥伦比亚大学）；Massachusetts Institute of Technology（麻省理工学院）；U.S. National Science Foundation National Center for Atmospheric Research（美国国家科学基金会国家大气研究中心）；University of Cambridge（剑桥大学）；Stony Brook University（石溪大学）；Google Research（谷歌研究）
Multi-Scale Dynamics of the Interaction Between Waves and Mean Flows: From Nonlinear WKB Theory to Gravity-Wave Parameterizations in Weather and Climate Models
Suêtes: An end-to-end differentiable non-hydrostatic limited-area dynamical core
University of British Columbia（不列颠哥伦比亚大学）；Université du Québec à Montréal（蒙特利尔大学）；University of Saskatchewan（萨斯喀彻温大学）；Memorial University of Newfoundland（纽芬兰纪念大学）
A Model Intercomparison Study of Mixed-Phase Clouds in a Laboratory Chamber
Pacific Northwest National Laboratory（太平洋西北国家实验室）；National Center for Atmospheric Research（美国国家大气研究中心）；The University of Utah（犹他大学）；University of Warsaw, Faculty of Physics, Institute of Geophysics（华沙大学物理学院地球物理研究所）；University of Hyogo（兵库大学）；Freie Universität Berlin（柏林自由大学）；University of Gothenburg（哥德堡大学）；Chalmers University of Technology（查尔姆斯理工大学）；Leibniz Institute for Tropospheric Research（莱布尼茨对流层研究所）；Brookhaven National Laboratory（布鲁克海文国家实验室）；Michigan Technological University（密歇根理工大学）
CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints
Department of Mechanical Engineering, National University of Singapore（新加坡国立大学机械工程系）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；NVIDIA AI Technology Centre（NVIDIA人工智能技术中心）；Centre for Climate Research Singapore（新加坡气候研究中心）；Environmental Science Division, Argonne National Laboratory（阿贡国家实验室环境科学部）；Information Sciences and Technology Department, The Pennsylvania State University（宾夕法尼亚州立大学信息科学与技术系）
