Articles | Volume 15, issue 9
https://doi.org/10.5194/gmd-15-3923-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-15-3923-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Stable climate simulations using a realistic general circulation model with neural network parameterizations for atmospheric moist physics and radiation processes
Department of Computer Science and Technology, Tsinghua University,
Beijing, 100084, China
Yilun Han
CORRESPONDING AUTHOR
Department of Earth System Science, Tsinghua University, Beijing,
100084, China
Wei Xue
CORRESPONDING AUTHOR
Department of Computer Science and Technology, Tsinghua University,
Beijing, 100084, China
Guangwen Yang
Department of Computer Science and Technology, Tsinghua University,
Beijing, 100084, China
Guang J. Zhang
Scripps Institution of Oceanography, La Jolla, CA, USA
Related authors
No articles found.
Jonathon S. Wright, Shenglong Zhang, Jiao Chen, Sean M. Davis, Paul Konopka, Mengqian Lu, Xiaolu Yan, and Guang J. Zhang
Atmos. Chem. Phys., 25, 9617–9643, https://doi.org/10.5194/acp-25-9617-2025, https://doi.org/10.5194/acp-25-9617-2025, 2025
Short summary
Short summary
Atmospheric reanalysis products reconstruct past states of the atmosphere. These products are often used to study winds and temperatures in the upper-level monsoon circulation, but their ability to reproduce composition fields like water vapor and ozone has been questionable at best. Here we report clear signs of improvement in both consistency across reanalyses and agreement with satellite observations, outline limitations, and suggest steps to further enhance the usefulness of these fields.
Yiming Wang, Yi Zhang, Yilun Han, Wei Xue, Yihui Zhou, Xiaohan Li, and Haishan Chen
EGUsphere, https://doi.org/10.5194/egusphere-2025-2790, https://doi.org/10.5194/egusphere-2025-2790, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
This work explores the use of global storm-resolving model (GSRM) simulation data to enhance global climate modeling (GCM) through a machine learning–based model physics suite. Stable multiyear climate simulations with improved precipitation characteristics are achieved by using 80-day GSRM data.
Lilong Zhou and Wei Xue
EGUsphere, https://doi.org/10.5194/egusphere-2025-1889, https://doi.org/10.5194/egusphere-2025-1889, 2025
Short summary
Short summary
This study develops a novel physics-based weather prediction model using artificial intelligence development platforms, achieving high accuracy while maintaining strict physical conservation laws. Our algorithms are optimized for modern super computers, enabling efficient large-scale weather simulations. A key innovation is the model's inherent differentiable nature, allowing seamless integration with AI systems to enhance predictive capabilities through machine learning techniques.
Shenglong Zhang, Jiao Chen, Jonathon S. Wright, Sean M. Davis, Jie Gao, Paul Konopka, Ninghui Li, Mengqian Lu, Susann Tegtmeier, Xiaolu Yan, Guang J. Zhang, and Nuanliang Zhu
EGUsphere, https://doi.org/10.5194/egusphere-2025-543, https://doi.org/10.5194/egusphere-2025-543, 2025
Short summary
Short summary
This study examines water vapor changes in the upper atmosphere above the Asian summer monsoon using satellite data and climate models. Three key patterns of variability were identified: year-to-year changes, and two shifting distributions driven by weather and monsoon dynamics. Despite uncertainties, modern models are improving in capturing these processes. This enhances understanding of water vapor’s role in the upper atmosphere.
Siyuan Chen, Yi Zhang, Yiming Wang, Zhuang Liu, Xiaohan Li, and Wei Xue
Geosci. Model Dev., 17, 6301–6318, https://doi.org/10.5194/gmd-17-6301-2024, https://doi.org/10.5194/gmd-17-6301-2024, 2024
Short summary
Short summary
This study explores strategies and techniques for implementing mixed-precision code optimization within an atmosphere model dynamical core. The coded equation terms in the governing equations that are sensitive (or insensitive) to the precision level have been identified. The performance of mixed-precision computing in weather and climate simulations was analyzed.
Jiaxu Guo, Juepeng Zheng, Yidan Xu, Haohuan Fu, Wei Xue, Lanning Wang, Lin Gan, Ping Gao, Wubing Wan, Xianwei Wu, Zhitao Zhang, Liang Hu, Gaochao Xu, and Xilong Che
Geosci. Model Dev., 17, 3975–3992, https://doi.org/10.5194/gmd-17-3975-2024, https://doi.org/10.5194/gmd-17-3975-2024, 2024
Short summary
Short summary
To enhance the efficiency of experiments using SCAM, we train a learning-based surrogate model to facilitate large-scale sensitivity analysis and tuning of combinations of multiple parameters. Employing a hybrid method, we investigate the joint sensitivity of multi-parameter combinations across typical cases, identifying the most sensitive three-parameter combination out of 11. Subsequently, we conduct a tuning process aimed at reducing output errors in these cases.
Yong Wang, Wenwen Xia, and Guang J. Zhang
Atmos. Chem. Phys., 21, 16797–16816, https://doi.org/10.5194/acp-21-16797-2021, https://doi.org/10.5194/acp-21-16797-2021, 2021
Short summary
Short summary
This study developed a novel approach to detect what rainfall rates climatologically are most efficient for wet removal of different aerosol types and applied it to a global climate model (GCM). Results show that light rain has disproportionate control on aerosol wet scavenging, with distinct rain rates for different aerosol sizes. The approach can be applied to other GCMs to better understand the aerosol wet scavenging by rainfall, which is important to better simulate aerosols.
Tongwen Wu, Rucong Yu, Yixiong Lu, Weihua Jie, Yongjie Fang, Jie Zhang, Li Zhang, Xiaoge Xin, Laurent Li, Zaizhi Wang, Yiming Liu, Fang Zhang, Fanghua Wu, Min Chu, Jianglong Li, Weiping Li, Yanwu Zhang, Xueli Shi, Wenyan Zhou, Junchen Yao, Xiangwen Liu, He Zhao, Jinghui Yan, Min Wei, Wei Xue, Anning Huang, Yaocun Zhang, Yu Zhang, Qi Shu, and Aixue Hu
Geosci. Model Dev., 14, 2977–3006, https://doi.org/10.5194/gmd-14-2977-2021, https://doi.org/10.5194/gmd-14-2977-2021, 2021
Short summary
Short summary
This paper presents the high-resolution version of the Beijing Climate Center (BCC) Climate System Model, BCC-CSM2-HR, and describes its climate simulation performance including the atmospheric temperature and wind; precipitation; and the tropical climate phenomena such as TC, MJO, QBO, and ENSO. BCC-CSM2-HR is our model version contributing to the HighResMIP. We focused on its updates and differential characteristics from its predecessor, the medium-resolution version BCC-CSM2-MR.
Yong Wang, Guang J. Zhang, Shaocheng Xie, Wuyin Lin, George C. Craig, Qi Tang, and Hsi-Yen Ma
Geosci. Model Dev., 14, 1575–1593, https://doi.org/10.5194/gmd-14-1575-2021, https://doi.org/10.5194/gmd-14-1575-2021, 2021
Short summary
Short summary
A stochastic deep convection parameterization is implemented into the US Department of Energy Energy Exascale Earth System Model Atmosphere Model version 1 (EAMv1). Compared to the default model, the well-known problem of
too much light rain and too little heavy rainis largely alleviated over the tropics with the stochastic scheme. Results from this study provide important insights into the model performance of EAMv1 when stochasticity is included in the deep convective parameterization.
Jingyu Wang, Jiwen Fan, Robert A. Houze Jr., Stella R. Brodzik, Kai Zhang, Guang J. Zhang, and Po-Lun Ma
Geosci. Model Dev., 14, 719–734, https://doi.org/10.5194/gmd-14-719-2021, https://doi.org/10.5194/gmd-14-719-2021, 2021
Short summary
Short summary
This paper presents an evaluation of the E3SM model against NEXRAD radar observations for the warm seasons during 2014–2016. The COSP forward simulator package is implemented in the model to generate radar reflectivity, and the NEXRAD observations are coarsened to the model resolution for comparison. The model severely underestimates the reflectivity above 4 km. Sensitivity tests on the parameters from cumulus parameterization and cloud microphysics do not improve this model bias.
Shaoqing Zhang, Haohuan Fu, Lixin Wu, Yuxuan Li, Hong Wang, Yunhui Zeng, Xiaohui Duan, Wubing Wan, Li Wang, Yuan Zhuang, Hongsong Meng, Kai Xu, Ping Xu, Lin Gan, Zhao Liu, Sihai Wu, Yuhu Chen, Haining Yu, Shupeng Shi, Lanning Wang, Shiming Xu, Wei Xue, Weiguo Liu, Qiang Guo, Jie Zhang, Guanghui Zhu, Yang Tu, Jim Edwards, Allison Baker, Jianlin Yong, Man Yuan, Yangyang Yu, Qiuying Zhang, Zedong Liu, Mingkui Li, Dongning Jia, Guangwen Yang, Zhiqiang Wei, Jingshan Pan, Ping Chang, Gokhan Danabasoglu, Stephen Yeager, Nan Rosenbloom, and Ying Guo
Geosci. Model Dev., 13, 4809–4829, https://doi.org/10.5194/gmd-13-4809-2020, https://doi.org/10.5194/gmd-13-4809-2020, 2020
Short summary
Short summary
Science advancement and societal needs require Earth system modelling with higher resolutions that demand tremendous computing power. We successfully scale the 10 km ocean and 25 km atmosphere high-resolution Earth system model to a new leading-edge heterogeneous supercomputer using state-of-the-art optimizing methods, promising the solution of high spatial resolution and time-varying frequency. Corresponding technical breakthroughs are of significance in modelling and HPC design communities.
Cited articles
Bony, S., Stevens, B., Frierson, D. M. W., Jakob, C., Kageyama, M., Pincus,
R., Shepherd, T. G., Sherwood, S. C., Siebesma, A. P., Sobel, A. H.,
Watanabe, M., and Webb, M. J.: Clouds, circulation and climate sensitivity,
Nat. Geosci., 8, 261–268, https://doi.org/10.1038/ngeo2398, 2015.
Brenowitz, N. D. and Bretherton, C. S.: Spatially Extended Tests of a Neural
Network Parametrization Trained by Coarse-Graining, J. Adv.
Model. Earth Syst., 11, 2728–2744, https://doi.org/10.1029/2019ms001711, 2019.
Brenowitz, N. D., Beucler, T., Pritchard, M., and Bretherton, C. S.:
Interpreting and Stabilizing Machine-Learning Parametrizations of
Convection, J. Atmos. Sci., 77, 4357–4375,
https://doi.org/10.1175/jas-d-20-0082.1, 2020.
Bretherton, C. S., Blossey, P. N., and Stan, C.: Cloud feedbacks on
greenhouse warming in the superparameterized climate model SP-CCSM4, J. Adv. Model. Earth Syst., 6, 1185–1204,
https://doi.org/10.1002/2014MS000355, 2014.
Cao, G. and Zhang, G. J.: Role of Vertical Structure of Convective Heating
in MJO Simulation in NCAR CAM5.3, J. Climate, 30, 7423–7439,
https://doi.org/10.1175/jcli-d-16-0913.1, 2017.
Emanuel, K. A., David Neelin, J., and Bretherton, C. S.: On large-scale
circulations in convecting atmospheres, Q. J. Roy.
Meteorol. Soc., 120, 1111–1143, https://doi.org/10.1002/qj.49712051902, 1994.
Feng, Z., Leung, L. R., Houze Jr., R. A., Hagos, S., Hardin, J., Yang, Q., Han, B., and Fan, J.: Structure and Evolution of Mesoscale Convective Systems: Sensitivity to Cloud Microphysics in Convection-Permitting Simulations Over the United States, J. Adv. Model. Earth Syst., 10, 1470–1494, https://doi.org/10.1029/2018ms001305, 2018.
Gentine, P., Pritchard, M., Rasp, S., Reinaudi, G., and Yacalis, G.: Could
machine learning break the convection parameterization deadlock?,
Geophys. Res. Lett., 45, 5742–5751, 2018.
Gettelman, A., Liu, X., Ghan, S. J., Morrison, H., Park, S., Conley, A. J.,
Klein, S. A., Boyle, J., Mitchell, D. L., and Li, J.-L. F.: Global
simulations of ice nucleation and ice supersaturation with an improved cloud
scheme in the Community Atmosphere Model, J. Geophys. Res.-Atmos., 115, https://doi.org/10.1029/2009JD013797, 2010.
Goodfellow, I., Bengio, Y., and Courville, A.: Deep learning, MIT
press, http://www.deeplearningbook.org (last access: 9 May 2022), 2016.
Grabowski, W. W.: Coupling Cloud Processes with the Large-Scale Dynamics
Using the Cloud-Resolving Convection Parameterization (CRCP), J.
Atmos. Sci., 58, 978–997, https://doi.org/10.1175/1520-0469(2001)058<0978:Ccpwtl>2.0.Co;2, 2001.
Grabowski, W. W.: An Improved Framework for Superparameterization, J. Atmos. Sci., 61, 1940–1952,
https://doi.org/10.1175/1520-0469(2004)061<1940:Aiffs>2.0.Co;2, 2004.
Grabowski, W. W. and Smolarkiewicz, P. K.: CRCP: a Cloud Resolving
Convection Parameterization for modeling the tropical convecting atmosphere,
Physica D, 133, 171–178,
https://doi.org/10.1016/S0167-2789(99)00104-9, 1999.
Han, Y., Zhang, G. J., Huang, X., and Wang, Y.: A Moist Physics
Parameterization Based on Deep Learning, J. Adv. Model.
Earth Syst., 12, e2020MS002076, https://doi.org/10.1029/2020ms002076, 2020.
Holloway, C. E., Woolnough, S. J., and Lister, G. M. S.: Precipitation
distributions for explicit versus parametrized convection in a large-domain
high-resolution tropical case study, Q. J. Roy.
Meteorol. Soc., 138, 1692–1708, https://doi.org/10.1002/qj.1903,
2012.
Hornik, K., Stinchcombe, M., and White, H.: Multilayer feedforward networks
are universal approximators, Neural Net., 2, 359–366,
https://doi.org/10.1016/0893-6080(89)90020-8, 1989.
Huffman, G. J., Alder, R. F., Bolvin, D. T., Gu, G., Nelkin, E. J., Bowman, K. P., Hong, Y., Stocker, E. F., and Wolff, D. B.: The TRMM multisatellite image precipitation analysis (TMPA). Quasi-global, multi-year, combined-sensor precipitation estimates at fine scales, J. Hydrometeor., 8, 38–55, 2007.
Jiang, X., Waliser, D. E., Xavier, P. K., Petch, J., Klingaman, N. P.,
Woolnough, S. J., Guan, B., Bellon, G., Crueger, T., DeMott, C., Hannay, C.,
Lin, H., Hu, W., Kim, D., Lappen, C.-L., Lu, M.-M., Ma, H.-Y., Miyakawa, T.,
Ridout, J. A., Schubert, S. D., Scinocca, J., Seo, K.-H., Shindo, E., Song,
X., Stan, C., Tseng, W.-L., Wang, W., Wu, T., Wu, X., Wyser, K., Zhang, G.
J., and Zhu, H.: Vertical structure and physical processes of the
Madden-Julian oscillation: Exploring key model physics in climate
simulations, J. Geophys. Res.-Atmos., 120, 4718–4748,
https://doi.org/10.1002/2014jd022375, 2015.
Jin, Y. and Stan, C.: Simulation of East Asian Summer Monsoon (EASM) in SP-CCSM4: Part I – Seasonal mean state and intraseasonal variability, J. Geophys. Res.-Atmos., 121, 7801–7818, https://doi.org/10.1002/2015JD024035, 2016.
Khairoutdinov, M., Randall, D., and DeMott, C.: Simulations of the
Atmospheric General Circulation Using a Cloud-Resolving Model as a
Superparameterization of Physical Processes, J. Atmos.
Sci., 62, 2136–2154, https://doi.org/10.1175/jas3453.1, 2005.
Khairoutdinov, M. F. and Randall, D. A.: A cloud resolving model as a cloud
parameterization in the NCAR Community Climate System Model: Preliminary
results, Geophys. Res. Lett., 28, 3617–3620, https://doi.org/10.1029/2001gl013552,
2001.
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv
preprint arXiv:1412.6980, 2014.
Kooperman, G. J., Pritchard, M. S., Burt, M. A., Branson, M. D., and
Randall, D. A.: Robust effects of cloud superparameterization on simulated
daily rainfall intensity statistics across multiple versions of the
Community Earth System Model, J. Adv. Model. Earth Syst.,
8, 140–165, https://doi.org/10.1002/2015ms000574, 2016.
Krasnopolsky, V. M., Fox-Rabinovitz, M. S., and Belochitski, A. A.: Using
ensemble of neural networks to learn stochastic convection parameterizations
for climate and numerical weather prediction models from data simulated by a
cloud resolving model, Adv. Artif. Neural Syst., 2013, 485913, https://doi.org/10.1155/2013/485913, 2013.
Lin, J.-L.: The Double-ITCZ Problem in IPCC AR4 Coupled GCMs:
Ocean–Atmosphere Feedback Analysis, J. Climate, 20, 4497–4525,
https://doi.org/10.1175/jcli4272.1, 2007.
Ling, J., Li, C., Li, T., Jia, X., Khouider, B., Maloney, E., Vitart, F.,
Xiao, Z., and Zhang, C.: Challenges and Opportunities in MJO Studies,
B. Am. Meteorol. Soc., 98, ES53–ES56,
https://doi.org/10.1175/bams-d-16-0283.1, 2017.
Lopez-Gomez, I., Cohen, Y., He, J., Jaruga, A., and Schneider, T.: A
Generalized Mixing Length Closure for Eddy-Diffusivity Mass-Flux Schemes of
Turbulence and Convection, J. Adv. Model. Earth Sys.,
12, e2020MS002161, https://doi.org/10.1029/2020MS002161, 2020.
Loshchilov, I. and Hutter, F.: Sgdr: Stochastic gradient descent with warm
restarts, arXiv preprint arXiv:1608.03983, 2016.
Madden, R. A. and Julian, P. R.: Description of Global-Scale Circulation
Cells in the Tropics with a 40–50 Day Period, J. Atmos.
Sciences, 29, 1109–1123, https://doi.org/10.1175/1520-0469(1972)029<1109:Dogscc>2.0.Co;2, 1972.
Mooers, G., Pritchard, M., Beucler, T., Ott, J., Yacalis, G., Baldi, P., and
Gentine, P.: Assessing the Potential of Deep Learning for Emulating Cloud
Superparameterization in Climate Models With Real-Geography Boundary
Conditions, J. Adv. Model. Earth Syst., 13,
e2020MS002385, https://doi.org/10.1029/2020MS002385, 2021.
Morrison, H. and Gettelman, A.: A New Two-Moment Bulk Stratiform Cloud
Microphysics Scheme in the Community Atmosphere Model, Version 3 (CAM3).
Part I: Description and Numerical Tests, J. Climate, 21, 3642–3659,
https://doi.org/10.1175/2008jcli2105.1, 2008.
Neale, R. B., Chen, C.-C., Gettelman, A., Lauritzen, P. H., Park, S.,
Williamson, D. L., Conley, A. J., Garcia, R., Kinnison, D., and Lamarque,
J.-F.: Description of the NCAR community atmosphere model (CAM 5.0), NCAR
Technical Note, 1, 1–12, 2012.
O'Gorman, P. A. and Dwyer, J. G.: Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events, J. Adv. Model. Earth Syst., 10, 2548–2563, https://doi.org/10.1029/2018ms001351, 2018.
Oleson, K. W., Lawrence, D. M., B, G., Flanner, M. G., Kluzek, E., J, P., Levis, S., Swenson, S. C., Thornton, E., Feddema, J., Heald, C. L., Lamarque, J., Niu, G., Qian, T., Running, S., Sakaguchi, K., Yang, L., Zeng, X., Zeng, X., and Decker, M.: Technical Description of version 4.0 of the Community Land Model (CLM), 266, https://doi.org/10.5065/D6FB50WZ, 2010.
Ott, J., Pritchard, M., Best, N., Linstead, E., Curcic, M., and Baldi, P.: A
Fortran-Keras Deep Learning Bridge for Scientific Computing, Sci.
Programm., 2020, 8888811, https://doi.org/10.1155/2020/8888811, 2020.
Park, S. and Bretherton, C. S.: The University of Washington Shallow
Convection and Moist Turbulence Schemes and Their Impact on Climate
Simulations with the Community Atmosphere Model, J. Climate, 22,
3449–3469, https://doi.org/10.1175/2008jcli2557.1, 2009.
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., and Desmaison, A.: Pytorch: An imperative style, high-performance deep learning library, Adv. Neural Inform. Process. Syst., 32, https://doi.org/10.48550/arXiv.1912.01703, arxiv, Cornell University, 2019.
Randall, D., Khairoutdinov, M., Arakawa, A., and Grabowski, W.: Breaking the
Cloud Parameterization Deadlock, B. Am. Meteorol.
Soc., 84, 1547–1564, https://doi.org/10.1175/bams-84-11-1547, 2003.
Rasp, S.: Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations: general algorithms and Lorenz 96 case study (v1.0), Geosci. Model Dev., 13, 2185–2196, https://doi.org/10.5194/gmd-13-2185-2020, 2020.
Rasp, S., Pritchard, M. S., and Gentine, P.: Deep learning to represent
subgrid processes in climate models, P. Natl. Acad.
Sci. USA, 115, 9684–9689, https://doi.org/10.1073/pnas.1810286115, 2018.
Song, X. and Zhang, G. J.: The Roles of Convection Parameterization in the
Formation of Double ITCZ Syndrome in the NCAR CESM: I. Atmospheric
Processes, J. Adv. Model. Earth Syst., 10, 842–866,
https://doi.org/10.1002/2017MS001191, 2018.
Tiedtke, M.: A Comprehensive Mass Flux Scheme for Cumulus Parameterization
in Large-Scale Models, Mon. Weather Rev., 117, 1779–1800,
https://doi.org/10.1175/1520-0493(1989)117<1779:Acmfsf>2.0.Co;2, 1989.
Wang, X. and Han, Y.: Data for “Stable climate simulations using a realistic GCM with neural network parameterizations for atmospheric moist physics and radiation processes”, Zenodo [data set], https://doi.org/10.5281/zenodo.5625616, 2021a.
Wang, X. and Han, Y.: Codes for “Stable climate simulations using a realistic GCM with neural network parameterizations for atmospheric moist physics and radiation processes”, Zenodo [code], https://doi.org/10.5281/zenodo.5596273, 2021b.
Wheeler, M. and Kiladis, G. N.: Convectively Coupled Equatorial Waves:
Analysis of Clouds and Temperature in the Wavenumber–Frequency Domain,
J. Atmos. Sci., 56, 374–399,
https://doi.org/10.1175/1520-0469(1999)056<0374:Ccewao>2.0.Co;2, 1999.
Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., and Finn, C.: Gradient surgery for multi-task learning, Adv. Neural Info. Process. Syst., 33, 5824–5836, 2020.
Yuval, J. and O'Gorman, P. A.: Stable machine-learning parameterization of
subgrid processes for climate modeling at a range of resolutions, Nat.
Commun., 11, 3295, https://doi.org/10.1038/s41467-020-17142-3, 2020.
Yuval, J., O'Gorman, P. A., and Hill, C. N.: Use of Neural Networks for
Stable, Accurate and Physically Consistent Parameterization of Subgrid
Atmospheric Processes With Good Performance at Reduced Precision,
Geophys. Res. Lett., 48, e2020GL091363,
https://doi.org/10.1029/2020GL091363, 2021.
Zhang, G. J. and McFarlane, N. A.: Sensitivity of climate simulations to the
parameterization of cumulus convection in the Canadian climate centre
general circulation model, Atmos.-Ocean, 33, 407–446,
https://doi.org/10.1080/07055900.1995.9649539, 1995.
Zhang, G. J. and Song, X.: Convection Parameterization, Tropical Pacific
Double ITCZ, and Upper-Ocean Biases in the NCAR CCSM3. Part II: Coupled
Feedback and the Role of Ocean Heat Transport, J. Climate, 23,
800–812, https://doi.org/10.1175/2009jcli3109.1, 2010.
Zhang, G. J., Song, X., and Wang, Y.: The double ITCZ syndrome in GCMs: A
coupled feedback problem among convection, clouds, atmospheric and ocean
circulations, Atmos. Res., 229, 255–268,
https://doi.org/10.1016/j.atmosres.2019.06.023, 2019.
Short summary
This study uses a set of deep neural networks to learn a parameterization scheme from a superparameterized general circulation model (GCM). After being embedded in a realistically configurated GCM, the parameterization scheme performs stably in long-term climate simulations and reproduces reasonable climatology and climate variability. This success is the first for long-term stable climate simulations using machine learning parameterization under real geographical boundary conditions.
This study uses a set of deep neural networks to learn a parameterization scheme from a...