气候变化领域集成服务门户(CCPortal): Correcting Climate Model Sea Surface Temperature Simulations with Generative Adversarial Networks: Climatology, Interannual Variability, and Extremes

CCPortal

DOI	10.1007/s00376-024-3288-6
	Correcting Climate Model Sea Surface Temperature Simulations with Generative Adversarial Networks: Climatology, Interannual Variability, and Extremes
	Wang, Ya; Huang, Gang; Pan, Baoxiang; Lin, Pengfei; Boers, Niklas; Tao, Weichen; Chen, Yutong; Liu, Bo; Li, Haijie
发表日期	2024
ISSN	0256-1530
EISSN	1861-9533
英文摘要	Climate models are vital for understanding and projecting global climate change and its associated impacts. However, these models suffer from biases that limit their accuracy in historical simulations and the trustworthiness of future projections. Addressing these challenges requires addressing internal variability, hindering the direct alignment between model simulations and observations, and thwarting conventional supervised learning methods. Here, we employ an unsupervised Cycle-consistent Generative Adversarial Network (CycleGAN), to correct daily Sea Surface Temperature (SST) simulations from the Community Earth System Model 2 (CESM2). Our results reveal that the CycleGAN not only corrects climatological biases but also improves the simulation of major dynamic modes including the El Nino-Southern Oscillation (ENSO) and the Indian Ocean Dipole mode, as well as SST extremes. Notably, it substantially corrects climatological SST biases, decreasing the globally averaged Root-Mean-Square Error (RMSE) by 58%. Intriguingly, the CycleGAN effectively addresses the well-known excessive westward bias in ENSO SST anomalies, a common issue in climate models that traditional methods, like quantile mapping, struggle to rectify. Additionally, it substantially improves the simulation of SST extremes, raising the pattern correlation coefficient (PCC) from 0.56 to 0.88 and lowering the RMSE from 0.5 to 0.32. This enhancement is attributed to better representations of interannual, intraseasonal, and synoptic scales variabilities. Our study offers a novel approach to correct global SST simulations and underscores its effectiveness across different time scales and primary dynamical modes.
英文关键词	generative adversarial networks; model bias; deep learning; El Nino-Southern Oscillation; marine heatwaves
语种	英语
WOS研究方向	Meteorology & Atmospheric Sciences
WOS类目	Meteorology & Atmospheric Sciences
WOS记录号	WOS:001197362700001
来源期刊	ADVANCES IN ATMOSPHERIC SCIENCES
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/298889
作者单位	Chinese Academy of Sciences; Institute of Atmospheric Physics, CAS; Laoshan Laboratory; Chinese Academy of Sciences; University of Chinese Academy of Sciences, CAS; Technical University of Munich; Potsdam Institut fur Klimafolgenforschung; University of Exeter; University of Exeter; China Meteorological Administration; Chinese Academy of Meteorological Sciences (CAMS)
推荐引用方式 GB/T 7714	Wang, Ya,Huang, Gang,Pan, Baoxiang,et al. Correcting Climate Model Sea Surface Temperature Simulations with Generative Adversarial Networks: Climatology, Interannual Variability, and Extremes[J],2024.
APA	Wang, Ya.,Huang, Gang.,Pan, Baoxiang.,Lin, Pengfei.,Boers, Niklas.,...&Li, Haijie.(2024).Correcting Climate Model Sea Surface Temperature Simulations with Generative Adversarial Networks: Climatology, Interannual Variability, and Extremes.ADVANCES IN ATMOSPHERIC SCIENCES.
MLA	Wang, Ya,et al."Correcting Climate Model Sea Surface Temperature Simulations with Generative Adversarial Networks: Climatology, Interannual Variability, and Extremes".ADVANCES IN ATMOSPHERIC SCIENCES (2024).