Opportunities and challenges of artificial intelligence in climate research and services

doi:10.12006/j.issn.1673-1719.2024.158

Abstract

Abstract:

Climate change is a serious challenge to natural ecology and human society. As an important tool for addressing climate change, climate models provide important support for understanding the mechanism of the past climate system, climate services and projections of future global change scenarios. However, problems in process representation, subgrid parameterization and spatial resolution of climate models have severely limited their simulation and prediction capabilities. With the development of economy and society, artificial intelligence (AI) technology has been widely used, and its advantages of integrating multi-source data, identifying potential information, and learning from existing “experience” are expected to provide new assistance for climate research and application. Against this background, this paper firstly provides a concise review of the development of climate models, then combines the characteristics of AI on this basis to examine the application of AI in climate research and services, and analyzes the challenges faced at this stage. The results show that existing observational data and model outputs can provide a sufficient data base for AI applications, and AI can optimize and integrate climate models accordingly, thus improving the accuracy of climate simulation and prediction results. In the future, it is important to focus on the coupling of AI and climate models and to expand the application of AI in various areas of climate change, so as to more effectively address the challenges posed by global climate change.

Key words: Climate models, Artificial intelligence, Climate change

CHEN Deliang, TAN Xian-Chun, PENG Zhe, YAN Hong-Shuo, CHENG Yong-Long. Opportunities and challenges of artificial intelligence in climate research and services[J]. Climate Change Research, 2024, 20(6): 669-681.

Figures/Tables 1

References 88

[1]	秦大河. 全球气候变化对中国可持续发展的挑战[J]. 中国发展观察, 2007 (4): 38-39.
	Qin D H. The challenge of global climate change to China’s sustainable development[J]. China Development Observation, 2007 (4): 38-39 (in Chinese)
[2]	周波涛, 钱进. IPCC AR6报告解读: 极端天气气候事件变化[J]. 气候变化研究进展, 2021, 17 (6): 713-718.
	Zhou B T, Qian J. Changes of weather and climate extremes in the IPCC AR6[J]. Climate Change Research, 2021, 17 (6): 713-718 (in Chinese)
[3]	IPCC. Climate change 2021: the physical science basis[M]. Cambridge: Cambridge University Press, 2021
[4]	谭显春, 顾佰和, 王毅. 气候变化对我国中长期发展的影响分析及对策建议[J]. 中国科学院院刊, 2017, 32 (9): 1029-1035. DOI: 10.16418/j.issn.1000-3045.2017.09.013.
	Tan X C, Gu B H, Wang Y. Impact analysis and countermeasures for climate change on long-term development of China[J]. Bulletin of Chinese Academy of Sciences, 2017, 32 (9): 1029-1035. DOI: 10.16418/j.issn.1000-3045.2017.09.013 (in Chinese)
[5]	秦大河, 陈振林, 罗勇, 等. 气候变化科学的最新认知[J]. 气候变化研究进展, 2007, 3 (2): 63-73.
	Qin D H, Chen Z L, Luo Y, et al. Updated understanding of climate change sciences[J]. Climate Change Research, 2007, 3 (2): 63-73 (in Chinese)
[6]	周天军, 陈梓明, 邹立维, 等. 中国地球气候系统模式的发展及其模拟和预估[J]. 气象学报, 2020, 78 (3): 332-350.
	Zhou T J, Chen Z M, Zou L W, et al. Development of climate and Earth system models in China: past achievements and new CMIP6 results[J]. Acta Meteorologica Sinica, 2020, 78 (3): 332-350 (in Chinese)
[7]	张焓, 戴永久, 张树磊. 区域地球系统模式研究进展[J]. 大气科学学报, 2024, 47 (2): 216-223. DOI: 10.13878/j.cnki.dqkxxb.20240124012.
	Zhang H, Dai Y J, Zhang S L. A review of regional Earth system model development[J]. Transactions of Atmospheric Sciences, 2024, 47 (2): 216-223. DOI: 10.13878/j.cnki.dqkxxb.20240124012 (in Chinese)
[8]	Hill C, Deluca C, Balaji V, et al. The architecture of the Earth system modeling framework[J]. Computing in Science & Engineering, 2004, 6 (1): 18-28. DOI: 10.1109/MCISE.2004.1255817
[9]	张仲石, 李双林, 王会军, 等. 浅谈大气科学与地质学的学科交叉[J]. 地球科学, 2022, 47 (10): 3569-3579.
	Zhang Z S, Li S L, Wang H J, et al. Introduction of crossing disciplines between geology and atmospheric science[J]. Earth Science, 2022, 47 (10): 3569-3579 (in Chinese)
[10]	王勇, 刘苏峡, 邵亚平, 等. 简单地球模型的研究进展[J]. 气象科技进展, 2014, 4 (3): 26-31. DOI: 10.3969/j.issn.2095-1973.2014.03.004.
	Wang Y, Liu S X, Shao Y P, et al. Progress in simple Earth models[J]. Advances in Meteorological Science and Technology, 2014, 4 (3): 26-31. DOI: 10.3969/j.issn.2095-1973.2014.03.004 (in Chinese)
[11]	Manabe S, Bryan K. Climate calculations with a combined ocean-atmosphere model[J]. Journal of the Atmospheric Sciences, 1969, 26 (4): 786-789
[12]	Claussen M, Mysak L, Weaver A, et al. Earth system models of intermediate complexity: closing the gap in the spectrum of climate system models[J]. Climate Dynamics, 2002, 18 (7): 579-586. DOI: 10.1007/s00382-001-0200-1
[13]	周天军, 张文霞, 陈德亮, 等. 2021年诺贝尔物理学奖解读: 从温室效应到地球系统科学[J]. 中国科学: 地球科学, 2022, 52 (4): 579-594.
	Zhou T J, Zhang W X, Chen D, et al. Understanding and building upon the pioneering work of Nobel Prize in physics 2021 laureates Syukuro Manabe and Klaus Hasselmann: from the greenhouse effect to Earth system science and beyond[J]. Scientia Sinica Terrae, 2022, 52 (4): 579-594 (in Chinese)
[14]	Fan J, Han F, Liu H. Challenges of big data analysis[J]. National Science Review, 2014, 1 (2): 293-314. DOI: 10.1093/nsr/nwt032 pmid: 25419469
[15]	Li X, Feng M, Ran Y, et al. Big data in Earth system science and progress towards a digital twin[J]. Nature Reviews Earth & Environment, 2023. DOI: 10.1038/s43017-023-00409-w
[16]	秦昆, 周扬, 黄静, 等. 地球系统模式理论与技术研究综述[J]. 华南地理学报, 2023, 1 (1): 36-50. DOI: 10.20125/j.2097-2245.202301004.
	Qin K, Zhou Y, Huang J, et al. Review on the theories and technologies of the Earth system model[J]. South China Geographical Journal, 2023, 1 (1): 36-50. DOI: 10.20125/j.2097-2245.202301004 (in Chinese)
[17]	Villalba-Pradas A, Tapiador F J. Empirical values and assumptions in the convection of numerical models[J]. Copernicus GmbH, 2021. DOI: 10.5194/gmd-2021-61
[18]	周天军, 李立娟, 李红梅, 等. 气候变化的归因和预估模拟研究[J]. 大气科学, 2008, 32 (4): 906-922.
	Zhou T J, Li L J, Li H M, et al. Progress in climate change attribution and projection studies[J]. Chinese Journal of Atmospheric Sciences, 2008, 32 (4): 906-922 (in Chinese)
[19]	周天军, 张学洪, 王绍武. 大洋温盐环流与气候变率的关系[J]. 科学通报, 2000 (4): 421-425.
	Zhou T J, Zhang X L, Wang S W. Comments on the role of thermohaline circulation in global climate system[J]. Advance in Earth Sciences, 2000 (4): 421-425 (in Chinese)
[20]	谭显春, 戴瀚程, 顾佰和, 等. IPCC AR6报告历史排放趋势和驱动因素核心结论解读[J]. 气候变化研究进展, 2022, 18 (5): 538-545.
	Tan X C, Dai H C, Gu B H, et al. Analysis on the key findings related to emission trends and drivers from the IPCC AR6 report[J]. Climate Change Research, 2022, 18 (5): 538-545 (in Chinese)
[21]	钱诚, 张文霞. CMIP6检测归因模式比较计划(DAMIP)概况与评述[J]. 气候变化研究进展, 2019, 15 (5): 469-475.
	Qian C, Zhang W X. Short commentary on CMIP6 Detection and Attribution Model Intercomparison Project (DAMIP)[J]. Climate Change Research, 2019, 15 (5): 469-475 (in Chinese)
[22]	周天军, 陈梓明, 陈晓龙, 等. IPCC AR6报告解读: 未来的全球气候: 基于情景的预估和近期信息[J]. 气候变化研究进展, 2021, 17 (6): 652-663.
	Zhou T J, Chen Z M, Chen X L, et al. Interpreting IPCC AR6: future global climate based on projection under scenarios and on near-term information[J]. Climate Change Research, 2021, 17 (6): 652-663 (in Chinese)
[23]	Pirani A, Fuglestvedt J S, Byers E, et al. Scenarios in IPCC assessments: lessons from AR6 and opportunities for AR7[J]. NPJ Climate Action, 2024, 3 (1): 1-7. DOI: 10.1038/s44168-023-00082-1
[24]	谭显春, 郭雯, 樊杰, 等. 碳达峰、碳中和政策框架与技术创新政策研究[J]. 中国科学院院刊, 2022, 37 (4): 435-443.
	Tan X C, Guo W, Fan J, et al. Policy framework and technology innovation policy of carbon peak and carbon neutrality[J]. Bulletin of Chinese Academy of Sciences, 2022, 37 (4): 435-443 (in Chinese)
[25]	赵宗慈, 罗勇, 黄建斌. 极端天气与气候事件受到全球变暖影响吗?[J]. 气候变化研究进展, 2014, 10 (5): 388-390.
	Zhao Z C, Luo Y, Huang J B. Are extreme weather and climate events affected by global warming?[J]. Climate Change Research, 2014, 10 (5): 388-390 (in Chinese)
[26]	范雪薇, 缪驰远, 苟娇娇, 等. 国际耦合模式比较计划及其模拟能力研究进展[J]. 地理科学进展, 2023, 42 (6): 1204-1215. doi: 10.18306/dlkxjz.2023.06.015
	Fan X W, Miao C Y, Gou J J, et al. Coupled Model Intercomparison Project and its research progress in simulation performance[J]. Progress in Geography, 2023, 42 (6): 1204-1215 (in Chinese) doi: 10.18306/dlkxjz.2023.06.015
[27]	Yao S L, Luo J J, Huang G. Internal variability-generated uncertainty in East Asian climate projections estimated with 40 CCSM3 ensembles[J]. Plos One, 2016, 11 (3): e0149968. DOI: 10.1371/journal.pone.0149968
[28]	穆穆, 陈博宇, 周菲凡, 等. 气象预报的方法与不确定性[J]. 气象, 2011, 37 (1): 1-13.
	Mu M, Chen B Y, Zhou F F, et al. Methods and uncertainties of meteorological forecast[J]. Meteorological Monthly, 2011, 37 (1): 1-13 (in Chinese)
[29]	Palmer T N, Hagedorn R. Predictability of weather and climate[M]. Cambridge: Cambridge University Press, 2006: 157-180
[30]	Alizadeh O. Advances and challenges in climate modeling[J]. Climatic Change, 2022, 170 (1): 18. DOI: 10.1007/s10584-021-03298-4
[31]	丑纪范. 为什么要动力-统计相结合?兼论如何结合?[J]. 高原气象, 5 (4): 367-372.
	Chou J F. Why do we need to combine dynamics and statistics? How to combine them?[J]. Plateau Meteorology, 5 (4): 367-372 (in Chinese)
[32]	栾贻花, 俞永强, 郑伟鹏. 全球高分辨率气候系统模式研究进展[J]. 地球科学进展, 2016, 31 (3): 258-268. DOI: 10.11867/j.issn.1001-8166.2016.03.0258.
	Luan Y H, Yu Y Q, Zheng W P. Review of development and application of high resolution global climate system model[J]. Advances in Earth Science, 2016, 31 (3): 258-268. DOI: 10.11867/j.issn.1001-8166.2016.03.0258 (in Chinese)
[33]	刘永和, 郭维栋, 冯锦明, 等. 气象资料的统计降尺度方法综述[J]. 地球科学进展, 2011, 26 (8): 837-847.
	Liu Y H, Guo W D, Feng J M, et al. A summary of methods for statistical downscaling of meteorological data[J]. Advances in Earth Science, 2011, 26 (8): 837-847 (in Chinese)
[34]	Benestad R E, Hanssen-Bauer I, Chen D. Empirical-statistical downscaling[R/OL]. 2008 [2024-01-27]. https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2004EO420002
[35]	杨淑贤, 零丰华, 应武杉, 等. 人工智能技术气候预测应用简介[J]. 大气科学学报, 2022, 45 (5): 641-659.
	Yang S X, Ling F H, Ying W S, et al. A brief overview of the application of artificial intelligence to climate prediction[J]. Transactions of Atmospheric Sciences, 2022, 45 (5): 641-659 (in Chinese)
[36]	Luo J J, Yuan C, Sasaki W, et al. Current status of intraseasonal-seasonal-to-interannual prediction of the Indo-Pacific climate[R/OL]. 2016 [2024-01-27]. https://www.worldscientific.com/doi/10.1142/9789814696623_0003
[37]	Reichstein M, Camps-Valls G, Stevens B, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019 (7743). DOI: 10.1038/s41586-019-0912-1
[38]	Crevier D. AI: the tumultuous history of the search for artificial intelligence[J]. Science, 1993. DOI: 10.1126/science.261.5125.1186
[39]	Dey A. Machine learning algorithms: a review[J]. Computer Science, Mathematics, 2016, 7 (3): 1174-1179
[40]	Jones N. How machine learning could help to improve climate forecasts[J]. Nature, 2017, 548 (7668): 379. DOI: 10.1038/548379a
[41]	Kontokosta C E, Tull C. A data-driven predictive model of city-scale energy use in buildings[J]. Applied Energy, 2017, 197: 303-317. DOI: 10.1016/j.apenergy.2017.04.005
[42]	Racah E, Beckham C, Maharaj T, et al. Extreme weather: a large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events[J]. 31st Conference on Neural Information Processing System, 2016. DOI: 10.48550/arXiv.1612.02095
[43]	Gagne J D, McGovern, et al. Storm-based probabilistic hail forecasting with machine learning applied to convection-allowing ensembles[J]. Weather and Forecasting, 2017, 32. DOI: 10.1175/WAF-D-17-0010.1
[44]	赵宗慈, 罗勇, 黄建斌, 等. 人工智能应用于地球系统科学[J]. 气候变化研究进展, 2020, 16 (1): 126-129.
	Zhao Z C, Luo Y, Huang J B, et al. Artificial intelligence applies to Earth system science[J]. Climate Change Research, 2020, 16 (1): 126-129 (in Chinese)
[45]	贺洁颖, 唐伟, 周勇, 等. 人工智能在气象科学中应用的机遇和挑战[J]. 中国信息化, 2019 (12): 79-81.
	He J Y, Tang W, Zhou Y, et al. Opportunities and challenges for the application of artificial intelligence in meteorological science[J]. Informatization-Research, 2019 (12): 79-81 (in Chinese)
[46]	李新, 苏建宾. 走向数据善治: 以地球科学数据治理为例[J]. 科学通报, 2024, 69 (9): 1149-1155.
	Li X, Su J B. Towards good governance of data: a case study in geoscience data governance[J]. Science China Press, 2024, 69 (9): 1149-1155 (in Chinese)
[47]	Rolnick D, Donti P L, Kaack L H, et al. Tackling climate change with machine learning[J]. Computing Surveys, 2023. DOI: 10.1145/3485128
[48]	Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521 (7553): 436. DOI: 10.1038/nature14539
[49]	Dengel S, Zona D, Sachs T, et al. Testing the applicability of neural networks as a gap-filling method using CH₄ flux data from high latitude wetlands[J]. Biogeosciences, 2013, 10 (12): 8185-8200. DOI: 10.5194/bg-10-8185-2013
[50]	Beringer J, Mchugh I, Hutley L B, et al. Technical note: dynamic integrated gap-filling and partitioning for OzFlux (DINGO)[J]. Biogeosciences, 2017, 14 (6): 1-36. DOI: 10.5194/bg-14-1457-2017
[51]	郑欣彤, 边婷婷, 张德强, 等. 基于深度学习的温度观测数据长时间缺失值插补方法[J]. 计算机系统应用, 2022, 31 (4): 221-228. DOI: 10.15888/j.cnki.csa.008493.
	Zheng X T, Bian T T, Zhang D Q, et al. Interpolation of long time missing values of temperature based on deep learning[J]. Computer Systems & Applications, 2022, 31 (4): 221-228. DOI: 10.15888/j.cnki.csa.008493 (in Chinese)
[52]	El-Azhari A, Karaoui I, Brahim Y A, et al. Analyses of groundwater level in a data-scarce region based on assessed precipitation products and machine learning[J]. Groundwater for Sustainable Development, 2024, 26. DOI: 10.1016/j.gsd.2024.101299
[53]	王少影, 张宇, 孟宪红, 等. 机器学习算法对涡动相关缺失通量数据的插补研究[J]. 高原气象, 2020, 39 (6): 1348-1360. DOI: 10.7522/j.issn.1000-0534.2019.00142.
	Wang S Y, Zhang Y, Meng X H, et al. Fill the gaps of eddy covariance fluxes using machine learning algorithms[J]. Plateau Meteorology, 2020, 39 (6): 1348-1360. DOI: 10.7522/j.issn.1000-0534.2019.00142 (in Chinese)
[54]	Kadow C, Hall D M, Ulbrich U. Artificial intelligence reconstructs missing climate information[J]. Nature Geoscience, 2020 (13): 408-413
[55]	Lee Y, Wahba G, Ackerman S A, et al. Cloud classification of satellite radiance data by multicategory support vector machines 1 cloud classification revision[J]. Journal of Atmospheric and Oceanic Technology, 2004: 159-169
[56]	张飞, 闫杰. 基于深度卷积神经网络的云分类算法[J]. 西北工业大学学报, 2020, 38 (4): 740-746.
	Zhang F, Yan J. Cloud image classification method based on deep convolutional neural network[J]. Journal of Northwestern Polytechnical University, 2020, 38 (4): 740-746 (in Chinese)
[57]	Liu Y J, Racah E, Prabhat, et al. Application of deep convolutional neural networks for detecting extreme weather in climate datasets[C/OL]. 2016 [2024-01-27]. https://arxiv.org/abs/1605.01156
[58]	Toms B A, Barnes E A, Ebert-Uphoff I. Physically interpretable neural networks for the geosciences: applications to Earth system variability[J]. Journal of Advances in Modeling Earth Systems, 2020. DOI: 10.1029/2019MS002002
[59]	Lee Y J, Hall D, Stewart J, et al. Machine learning for targeted assimilation of satellite data[R/OL]. 2018 [2024-01-27]. https://dl.acm.org/doi/abs/10.1007/978-3-030-10997-4_4
[60]	Huntingford C, Marsh T, Scaife A A, et al. Potential influences on the United Kingdom’s floods of winter 2013/14[J]. Nature Climate Change, 2014, 4 (9): 769-777
[61]	Gilbert R C, Trafalis T B, Richman M B, et al. Machine learning methods for data assimilation[M]. US: The American Society of Mechanical Engineers Press, 2010
[62]	Arcucci R, Zhu J, Hu S, et al. Deep data assimilation: integrating deep learning with data assimilation[J]. Applied Sciences, 2021, 11 (3): 1114. DOI: 10.3390/app11031114
[63]	Wu P, Chang X, Sun J, et al. Fast data assimilation (FDA): data assimilation by machine learning for faster optimize model state[J]. Journal of Computational Science, 2021, 51 (7): 101323. DOI: 10.1016/j.jocs.2021.101323
[64]	Stengel K, Glaws A, Hettinger D, et al. Adversarial super-resolution of climatological wind and solar data[J]. Proceedings of the National Academy of Sciences, 2020, 117 (29): 201918964. DOI: 10.1073/pnas.1918964117
[65]	Rasp S, Lerch S. Neural networks for post-processing ensemble weather forecasts[J]. Monthly Weather Reviews, 2018, 146 (11): 3885-3900. DOI: 10.1175/mwr-d-18-0187.1
[66]	O’Gorman P A, Dwyer J G. Using Machine learning to parameterize moist convection: potential for modeling of climate, climate change, and extreme events[J]. Journal of Advances in Modeling Earth Systems, 2018. DOI: 10.1029/2018MS001351
[67]	Yuval J, O’Gorman P A. Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions[J]. Nature Communications, 2020, 11 (1). DOI: 10.1038/s41467-020-17142-3
[68]	Chen M, Fu H, Zhang T, et al. ResU-Deep: improving the trigger function of deep convection in tropical regions with deep learning[J]. Journal of Advances in Modeling Earth Systems, 2023, 15 (11): e2022MS003521. DOI: 10.1029/2022MS003521
[69]	Zhu Y Z, Zhang R H, Moum J N, et al. Physics-informed deep-learning parameterization of ocean vertical mixing improves climate simulations[J]. National Science Review, 2022 (8): 8. DOI: 10.1093/nsr/nwac044
[70]	Letu H, Ma R, Nakajima, et al. Surface solar radiation compositions observed from Himawari-8/9 and Fengyun-4 series[J]. Bulletin of the American Meteorological Society, 2023, 104 (10): 1772-1789
[71]	Chou C, Park J, Chou E. Generating high-resolution climate change projections using super-resolution convolutional LSTM neural networks[C]// IEEE 13th International Conference on Advanced Computational Intelligence, 2021. DOI: 10.1109/ICACI52617.2021.9435890
[72]	Ma Y, Liu T, Yu Z, et al. All-weather precipitable water vapor map reconstruction using data fusion and machine learning-based spatial downscaling[J]. Atmospheric Research, 2023, 296: 107068. DOI: 10.1016/j.atmosres.2023.107068
[73]	Sahar H P, Shamsuddin S, Chung E S, et al. Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh[J]. Atmospheric Research, 2018, 213: 149-162. DOI: 10.1016/j.atmosres.2018.06.006
[74]	Legasa M N, Manzanas R, Calvino A, et al. A posteriori random forests for stochastic downscaling of precipitation by predicting probability distributions[J]. Water Resources Research, 2022 (4): 58. DOI: 10.1029/2021WR030272
[75]	Hosseini B A, Norouzi E, Nourani V. Wavelet-based predictor screening for statistical downscaling of precipitation and temperature using the artificial neural network method[J]. Hydrology Research, 2022. DOI: 10.2166/nh.2022.094
[76]	Sachindra D A, Ahmed K, Md. Mamunur R, et al. Statistical downscaling of precipitation using machine learning techniques[J]. Atmospheric Research, 2018, 212: 240-258. DOI: 10.1016/j.atmosres.2018.05.022.6
[77]	Vandal T, Kodra E, Ganguly S, et al. DeepSD: generating high resolution climate change projections through single image super-resolution[J]. The ACM Digital Library, 2017: 1663-1672. DOI: 10.1145/3097983.3098004
[78]	Arcucci R, Zhu J, Hu S, et al. Deep data assimilation: integrating deep learning with data assimilation[J]. Applied Sciences, 2021, 11 (3): 1114. DOI: 10.3390/app11031114
[79]	Deo R C, Ahin M. Application of the extreme learning machine algorithm for the prediction of monthly effective drought index in eastern Australia[J]. Atmospheric Research, 2015, 153: 512-525. DOI: 10.1016/j.atmosres.2014.10.016
[80]	Ahlem F, Mejda C, Aya F. Spatio-temporal modeling of climate change impacts on drought forecast using generative adversarial network: a case study in Africa[J]. Expert Systems with Applications, 2024, 238: 122211. DOI: 10.1016/j.eswa.2023.122211
[81]	Huang G, Wang Y, Ham Y G, et al. Toward a learnable climate model in the artificial intelligence era[J]. Advances in Atmospheric Sciences, 2024, 41 (7): 1281-1288. DOI: 10.1007/s00376-024-3305-9
[82]	Chen L, Zhong X, Li H, et al. A machine learning model that outperforms conventional global subseasonal forecast models[J]. Nature Communications, 2024, 15 (1). DOI: 10.1038/s41467-024-50714-1
[83]	Kochkov D, Yuval J, Langmore I, et al. Neural general circulation models for weather and climate[J]. Nature, 2024, 632: 1060-1066
[84]	Zhu H, Jiang Z, Li L, et al. Intercomparison of multi-model ensemble-processing strategies within a consistent framework for climate projection in China[J]. Science China: Earth Sciences, 2023, 66 (9): 2125-2141. DOI: 10.1007/s11430-022-1154-7
[85]	智协飞, 王田, 季焱. 基于深度学习的中国地面气温的多模式集成预报研究[J]. 大气科学学报, 2020, 43 (3): 435-446. DOI: 10.13878/j.cnki.dqkxxb.20200219003.
	Zhi X F, Wang T, Ji Y. Multimodel ensemble forecasts of surface air temperature over China based on deep learning approach[J]. Transactions of Atmospheric Sciences, 2020, 43 (3): 435-446. DOI: 10.13878/j.cnki.dqkxxb.20200219003 (in Chinese)
[86]	Strobach E, Bel G. Improvement of climate predictions and reduction of their uncertainties using learning algorithms[J]. Atmospheric Chemistry and Physics, 2015, 15 (15): 8631-8641
[87]	Li T, Jiang Z, Le Treut H, et al. Machine learning to optimize climate projection over China with multi-model ensemble simulations[J]. Environmental Research Letters, 2021, 16 (9): 094028. DOI: 10.1088/1748-9326/ac1d0c
[88]	Jose D M, Vincent A M, Dwarakish G S. Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques[J]. Scientific Reports 2022, 12 (1): 4678. DOI: 10.1038/s41598-022-08786-w pmid: 35304552