Reconstruction of global surface ocean pCO(2) using region-specific predictors based on a stepwise FFNN regression algorithm

doi:10.5194/bg-19-845-2022

CORC > 海洋研究所 > 中国科学院海洋研究所 > 海洋生态与环境科学重点实验室

	Reconstruction of global surface ocean pCO(2) using region-specific predictors based on a stepwise FFNN regression algorithm
	Zhong, Guorong 1,2,3,4; Li, Xuegang 1,2,3,4; Song, Jinming 1,2,3,4; Qu, Baoxiao 1,2,4; Wang, Fan 1,2,3,4; Wang, Yanjun 1,4; Zhang, Bin 1,4; Sun, Xiaoxia 1,2,3,4; Zhang, Wuchang 1,2,4; Wang, Zhenyan 1,2,4
刊名	BIOGEOSCIENCES
	2022-02-10
卷号	19 期号:3 页码:845-859
ISSN号	1726-4170
DOI	10.5194/bg-19-845-2022
通讯作者	Li, Xuegang(lixuegang@qdio.ac.cn) ; Song, Jinming(jmsong@qdio.ac.cn)
英文摘要	Various machine learning methods were attempted in the global mapping of surface ocean partial pressure of CO2 (pCO(2)) to reduce the uncertainty of the global ocean CO2 sink estimate due to undersampling of pCO(2). In previous research, the predictors of pCO(2) were usually selected empirically based on theoretic drivers of surface ocean pCO(2), and the same combination of predictors was applied in all areas except where there was a lack of coverage. However, the differences between the drivers of surface ocean pCO(2) in different regions were not considered. In this work, we combined the stepwise regression algorithm and a feed-forward neural network (FFNN) to select predictors of pCO(2) based on the mean absolute error in each of the 11 biogeochemical provinces defined by the self-organizing map (SOM) method. Based on the predictors selected, a monthly global 1 circle x 1 circle surface ocean pCO(2) product from January 1992 to August 2019 was constructed. Validation of different combinations of predictors based on the Surface Ocean CO2 Atlas (SOCAT) dataset version 2020 and independent observations from time series stations was carried out. The prediction of pCO(2) based on region-specific predictors selected by the stepwise FFNN algorithm was more precise than that based on predictors from previous research. Applying the FFNN size-improving algorithm in each province decreased the mean absolute error (MAE) of the global estimate to 11.32 mu atm and the root mean square error (RMSE) to 17.99 mu atm. The script file of the stepwise FFNN algorithm and pCO(2) product are distributed through the Institute of Oceanology of the Chinese Academy of Sciences Marine Science Data Center (IOCAS, , Zhong, 2021.
资助项目	National Key Research and Development Program of China[2017YFA0603204] ; Major Program of the Pilot National Laboratory for Marine Science and Technology (Qingdao) in the 14th 5year Plan ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19060401] ; National Natural Science Foundation of China[91958103] ; National Natural Science Foundation of China[42176200] ; National Natural Science Foundation of China[41806133] ; Natural Science Foundation of Shandong Province[ZR2020YQ28]
WOS研究方向	Environmental Sciences & Ecology ; Geology
语种	英语
出版者	COPERNICUS GESELLSCHAFT MBH
WOS记录号	WOS:000758150300001
内容类型	期刊论文
源URL	[http://ir.qdio.ac.cn/handle/337002/178074]
专题	海洋研究所_海洋生态与环境科学重点实验室
通讯作者	Li, Xuegang; Song, Jinming
作者单位	1.Chinese Acad Sci, Ctr Ocean Megasci, Qingdao 266071, Peoples R China 2.Pilot Natl Lab Marine Sci & Technol, Marine Ecol & Environm Sci Lab, Qingdao 266237, Peoples R China 3.Univ Chinese Acad Sci, Beijing 101407, Peoples R China 4.Chinese Acad Sci, Inst Oceanol, Key Lab Marine Ecol & Environm Sci, Qingdao 266071, Peoples R China
推荐引用方式 GB/T 7714	Zhong, Guorong,Li, Xuegang,Song, Jinming,et al. Reconstruction of global surface ocean pCO(2) using region-specific predictors based on a stepwise FFNN regression algorithm[J]. BIOGEOSCIENCES,2022,19(3):845-859.
APA	Zhong, Guorong.,Li, Xuegang.,Song, Jinming.,Qu, Baoxiao.,Wang, Fan.,...&Duan, Liqin.(2022).Reconstruction of global surface ocean pCO(2) using region-specific predictors based on a stepwise FFNN regression algorithm.BIOGEOSCIENCES,19(3),845-859.
MLA	Zhong, Guorong,et al."Reconstruction of global surface ocean pCO(2) using region-specific predictors based on a stepwise FFNN regression algorithm".BIOGEOSCIENCES 19.3(2022):845-859.