文献类型： 外文期刊

作者： Han, Lang ¹ ; Yu, Gui-Rui ³ ; Chen, Zhi ³ ; Zhu, Xian-Jin ⁶ ; Zhang, Wei-Kang ³ ; Wang, Tie-Jun ¹ ; Xu, Li ³ ; Chen, Shi-Ping ⁷ ; Liu, Shao-Min ⁸ ; Wang, Hui-Min ³ ; Yan, Jun-Hua ⁹ ; Tan, Jun-Lei ¹⁰ ; Zhang, Fa-Wei ¹¹ ; Zhao, Feng-Hua ³ ; Li, Ying-Nian ¹¹ ; Zhang, Yi-Ping ¹² ; Sha, Li-Qing ¹² ; Song, Qing-Hai ¹² ; Shi, Pei-Li ³ ; Zhu, Jiao-Jun ¹³ ; Wu, Jia-Bing ¹³ ; Zhao, Zhong-Hui ¹⁴ ; Hao, Yan-Bin ¹⁵ ; Ji, Xi-Bin ¹⁰ ; Zhao, Liang ¹¹ ; Zhang, Yu-Cui ¹⁶ ; Jiang, Shi-Cheng ¹⁷ ; Gu, Feng-Xue ¹⁸ ; Wu, Zhi-Xiang ¹⁹ ; Zhang, Yang-Jian ³ ; Li, Zhou ²⁰ ; Tang, Ya-Kun ²¹ ; Jia, Bing-Rui ⁷ ; Dong, Gang ²² ; Gao, Yan-Hong ¹⁰ ; Jiang, Zheng-De ¹³ ; Sun, Dan ⁹ ; Wang, Jian-Lin ²³ ; He, Qi-Hua ²⁴ ; Li, Xin-Hu ²⁵ ; Wang, Fei ²⁶ ; Wei, Wen-Xue ²⁷ ; Deng, Zheng-Miao ²⁷ ; Hao, Xiang-Xiang ²⁸ ; Liu, Xiao-Li ²⁹ ; Zhang, Xi-Feng ³⁰ ; Mo, Xing-Guo ³¹ ; He, Yong-Tao ³ ; Liu, Xin-Wei ²⁴ ; Du, Hu ²⁷ ; Zhu, Zhi-Lin ³ ;

作者机构： 1.Tianjin Univ, Inst Surface Earth Syst Sci, Sch Earth Syst Sci, Tianjin, Peoples R China

2.Tianjin Univ, Tianjin Bohai Rim Coastal Earth Crit Zone Natl Ob, Tianjin, Peoples R China

3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Ecosyst Network Observat & Modeling, Beijing, Peoples R China

4.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China

5.Univ Chinese Acad Sci, Yanshan Earth Crit Zone & Surface Fluxes Res Stn, Beijing, Peoples R China

6.Shenyang Agr Univ, Coll Agron, Beijing, Peoples R China

7.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing, Peoples R China

8.Beijing Normal Univ, State Key Lab Earth Surface Proc & Resource Ecol, Fac Geog Sci, Beijing, Peoples R China

9.Chinese Acad Sci, South China Bot Garden, Guangzhou, Peoples R China

10.Chinese Acad Sci, Northwest Inst Ecoenvironm & Resources, Lanzhou, Peoples R China

11.Chinese Acad Sci, Northwest Inst Plateau Biol, Xining, Peoples R China

12.Chinese Acad Sci, Xishuangbanna Trop Bot Garden, Menglun, Peoples R China

13.Chinese Acad Sci, Inst Appl Ecol, Shenyang, Peoples R China

14.Cent South Univ Forestry & Technol, Changsha, Peoples R China

15.Univ Chinese Acad Sci, Beijing, Peoples R China

16.Chinese Acad Sci, Inst Genet & Dev Biol, Ctr Agr Resources Res, Shijiazhuang, Hebei, Peoples R China

17.Northeast Normal Univ, Sch Life Sci, Changchun, Peoples R China

18.Chinese Acad Agr Sci, Inst Environm & Sustainable Dev Agr, Beijing, Peoples R China

19.Chinese Acad Trop Agr Sci, Rubber Res Inst, Danzhou, Peoples R China

20.Chinese Acad Meteorol Sci, State Key Lab Severe Weather, Beijing, Peoples R China

21.Northwest A&F Univ, Xianyang, Peoples R China

22.Shanxi Univ, Taiyuan, Peoples R China

23.Qingdao Agr Univ, Coll Agron, Qingdao, Peoples R China

24.Chinese Acad Sci, Chengdu Inst Biol, Chengdu, Peoples R China

25.Chinese Acad Sci, Xinjiang Inst Ecol & Geog, Urumqi, Peoples R China

26.Inner Mongolia Agr Univ, Coll Forestry, Hohhot, Peoples R China

27.Chinese Acad Sci, Inst Subtrop Agr, Changsha, Peoples R China

28.Chinese Acad Sci, Northeast Inst Geog & Agroecol, Harbin, Peoples R China

29.Chinese Acad Sci, Inst Soil Sci, Nanjing, Peoples R China

30.Chinese Acad Sci, Inst Mt Hazards & Environm, Chengdu, Peoples R China

31.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Water Cycle & Its Related Land Proc, Beijing, Peoples R China

关键词： ecosystem respiration; eddy covariance; terrestrial ecosystem; machine learning; substrate; scale extension

期刊名称：GLOBAL BIOGEOCHEMICAL CYCLES （ 影响因子：6.5； 五年影响因子：7.067 ）

ISSN： 0886-6236

年卷期： 2022 年 36 卷 11 期

页码：

收录情况： SCI

摘要： Accurate estimation of regional and global patterns of ecosystem respiration (ER) is crucial to improve the understanding of terrestrial carbon cycles and the predictive ability of the global carbon budget. However, large uncertainties still exist in regional and global ER estimation due to the drawbacks of modeling methods. Based on eddy covariance ER data from 132 sites in China from 2002 to 2020, we established Intelligent Random Forest (IRF) models that integrated ecological understanding with machine learning techniques to estimate ER. The results showed that the IRF models performed better than semiempirical models and machine learning algorithms. The observed data revealed that gross primary productivity (GPP), living plant biomass, and soil organic carbon (SOC) were of great importance in controlling the spatiotemporal variability of ER across China. An optimal model governed by annual GPP, living plant biomass, SOC, and air temperature (IRF-04 model) matched 93% of the spatiotemporal variation in site-level ER, and was adopted to evaluate the spatiotemporal pattern of ER in China. Using the optimal model, we obtained that the annual value of ER in China ranged from 5.05 to 5.84 Pg C yr(-1) between 2000 and 2020, with an average value of 5.53 +/- 0.22 Pg C yr(-1). In this study, we suggest that future models should integrate process-based and data-driven approaches for understanding and evaluating regional and global carbon budgets.