气候变化领域集成服务门户(CCPortal): Technical note: Uncertainties in eddy covariance CO2fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches

CCPortal

DOI	10.5194/acp-21-15589-2021
	Technical note: Uncertainties in eddy covariance CO2fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches
	Yao J.; Gao Z.; Huang J.; Liu H.; Wang G.
发表日期	2021
ISSN	1680-7316
起始页码	15589
结束页码	15603
卷号	21 期号:20
英文摘要	Gap-filling eddy covariance CO2 fluxes is challenging at dryland sites due to small CO2 fluxes. Here, four machine learning (ML) algorithms including artificial neural network (ANN), k-nearest neighbors (KNNs), random forest (RF), and support vector machine (SVM) are employed and evaluated for gap-filling CO2 fluxes over a semiarid sagebrush ecosystem with different lengths of artificial gaps. The ANN and RF algorithms outperform the KNN and SVM in filling gaps ranging from hours to days, with the RF being more time efficient than the ANN. Performances of the ANN and RF are largely degraded for extremely long gaps of 2 months. In addition, our results suggest that there is no need to fill the daytime and nighttime net ecosystem exchange (NEE) gaps separately when using the ANN and RF. With the ANN and RF, the gap-filling-induced uncertainties in the annual NEE at this site are estimated to be within 16gCm-2, whereas the uncertainties by the KNN and SVM can be as large as 27gCm-2. To better fill extremely long gaps of a few months, we test a two-layer gap-filling framework based on the RF. With this framework, the model performance is improved significantly, especially for the nighttime data. Therefore, this approach provides an alternative in filling extremely long gaps to characterize annual carbon budgets and interannual variability in dryland ecosystems. © 2021 Jingyu Yao et al.
语种	英语
scopus关键词	algorithm; annual variation; artificial neural network; atmospheric chemistry; carbon budget; carbon monoxide; ecosystem dynamics; eddy covariance; gap dynamics; machine learning; net ecosystem exchange; uncertainty analysis; Artemisia tridentata
来源期刊	ATMOSPHERIC CHEMISTRY AND PHYSICS
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/246491
作者单位	Key Laboratory for Semi-Arid Climate Change, The Ministry of Education, College of Atmospheric Sciences, Lanzhou University, Lanzhou, China; Laboratory for Atmospheric Research, Department of Civil and Environmental Engineering, Washington State University, Pullman, WA, United States; School of Atmospheric Sciences, Sun Yat-sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, China; Collaborative Innovation Center for Western Ecological Safety, Lanzhou University, Lanzhou, China; Department of Atmospheric and Oceanic Sciences, Institute of Atmospheric Sciences, Fudan University, Shanghai, China
推荐引用方式 GB/T 7714	Yao J.,Gao Z.,Huang J.,et al. Technical note: Uncertainties in eddy covariance CO2fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches[J],2021,21(20).
APA	Yao J.,Gao Z.,Huang J.,Liu H.,&Wang G..(2021).Technical note: Uncertainties in eddy covariance CO2fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches.ATMOSPHERIC CHEMISTRY AND PHYSICS,21(20).
MLA	Yao J.,et al."Technical note: Uncertainties in eddy covariance CO2fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches".ATMOSPHERIC CHEMISTRY AND PHYSICS 21.20(2021).