Mapping Chinese annual gross primary productivity with eddy covariance measurements and machine learning

NWIPB OpenIR

	Mapping Chinese annual gross primary productivity with eddy covariance measurements and machine learning
	Zhu, XJ; Yu, GR; Chen, Z; Zhang, WK; Han, L; Wang, QF; Chen, SP; Liu, SM; Yan, JH; Zhang, FW; Zhao, FH; Li, YN; Zhang, YP; Shi, PL; Zhu, JJ; Wu, JB; Zhao, ZH; Hao, YB; Sha, LQ; Zhang, YC; Jiang, SC; Gu, FX; Wu, ZX; Wang, HM; Tan, JL; Zhang, YJ; Zhou, L; Tang, YK; Jia, BR; Li, YQ; Song, QH; Dong, G; Gao, YH; Jiang, ZD; Sun, D; Wang, JL; He, QH; Li, XH; Wang, F; Wei, WX; Deng, ZM; Hao, XX; Li, Y; Liu, XL; Zhang, XF; Zhu, ZL
	2023
发表期刊	SCIENCE OF THE TOTAL ENVIRONMENT
卷号	857
摘要	Annual gross primary productivity (AGPP) is the basis for grain production and terrestrial carbon sequestration. Map-ping regional AGPP from site measurements provides methodological support for analysing AGPP spatiotemporal var-iations thereby ensures regional food security and mitigates climate change. Based on 641 site-year eddy covariance measuring AGPP from China, we built an AGPP mapping scheme based on its formation and selected the optimal map-ping way, which was conducted through analysing the predicting performances of divergent mapping tools, variable combinations, and mapping approaches in predicting observed AGPP variations. The reasonability of the selected op-timal scheme was confirmed by assessing the consistency between its generating AGPP and previous products in spa-tiotemporal variations and total amount. Random forest regression tree explained 85 % of observed AGPP variations, outperforming other machine learning algorithms and classical statistical methods. Variable combinations containing climate, soil, and biological factors showed superior performance to other variable combinations. Mapping AGPP through predicting AGPP per leaf area (PAGPP) explained 86 % of AGPP variations, which was superior to other ap-proaches. The optimal scheme was thus using a random forest regression tree, combining climate, soil, and biological variables, and predicting PAGPP. The optimal scheme generating AGPP of Chinese terrestrial ecosystems decreased from southeast to northwest, which was highly consistent with previous products. The interannual trend and interan-nual variation of our generating AGPP showed a decreasing trend from east to west and from southeast to northwest, respectively, which was consistent with data-oriented products. The mean total amount of generated AGPP was 7.03 +/- 0.45 PgC yr-1 falling into the range of previous works. Considering the consistency between the generated AGPP and previous products, our optimal mapping way was suitable for mapping AGPP from site measurements. Our results provided a methodological support for mapping regional AGPP and other fluxes.
收录类别	SCIE
文献类型	期刊论文
条目标识符	http://210.75.249.4/handle/363003/61038
专题	中国科学院西北高原生物研究所
推荐引用方式 GB/T 7714	Zhu, XJ,Yu, GR,Chen, Z,et al. Mapping Chinese annual gross primary productivity with eddy covariance measurements and machine learning[J]. SCIENCE OF THE TOTAL ENVIRONMENT,2023,857.
APA	Zhu, XJ.,Yu, GR.,Chen, Z.,Zhang, WK.,Han, L.,...&Zhu, ZL.(2023).Mapping Chinese annual gross primary productivity with eddy covariance measurements and machine learning.SCIENCE OF THE TOTAL ENVIRONMENT,857.
MLA	Zhu, XJ,et al."Mapping Chinese annual gross primary productivity with eddy covariance measurements and machine learning".SCIENCE OF THE TOTAL ENVIRONMENT 857(2023).