Baseline map of organic carbon stock in farmland topsoil in East China

文献类型： 外文期刊

第一作者： Deng, Xunfei

作者： Deng, Xunfei;Chen, Xiaojia;Ma, Wanzhu;Ren, Zhouqiao;Long, Wenli;Lv, Xiaonan;Deng, Xunfei;Chen, Xiaojia;Ma, Wanzhu;Ren, Zhouqiao;Lv, Xiaonan;Zhang, Minghua;Grieneisen, Michael L.;Ni, Zhihua;Zhan, Yu

作者机构：

关键词： Soil organic carbon;Baseline map;Machine learning;Carbon accounting;Harmonized world soil database;Climate change

期刊名称：AGRICULTURE ECOSYSTEMS & ENVIRONMENT （ 影响因子：5.567； 五年影响因子：6.064 ）

ISSN： 0167-8809

年卷期： 2018 年 254 卷

页码：

收录情况： SCI

摘要： Soil organic carbon (SOC) is important to soil fertility and the global carbon cycle. Accurate estimates of SOC stock and its dynamics are critical for managing agricultural ecosystems and carbon accounting under climate change, especially for highly cultivated regions. We extensively surveyed the SOC levels in 29,927 sites in Zhejiang province, an intensively cultivated region of East China, from year 2007 to 2008. We then estimated the spatial distribution of topsoil (0-30 cm) organic carbon stock using a random forest (RF) model, which is a powerful machine learning algorithm with superior predictive performance over parametric statistical models. The final RF model contained 23 predictor variables, covering soil properties, vegetation, climate, topography, land cover, fanning practices, and locations. The RF model showed high performance in predicting the SOC stock, with a coefficient of determination (R-2) of 0.76 and a root mean square error (RMSE) of 10.63 t C ha(-1). This performance was superior to the General Linear Model (GLM) (R-2 = 0.35, RMSE = 19.93 t C ha(-1)) and the ordinary kriging (OK) method (R-2 = 0.57, RMSE = 14.44 t C ha(-1)), and was equivalent to Boosted Regressing Trees (BRT) (R-2 = 0.73, RMSE = 11.26 t C ha(-1)). According to the variable importance evaluation, soil properties were the most important predictor variables, followed by climate and location, with relative importance values of 61%, 17%, and 14%, respectively. The predicted SOC stock ranged from 14.8 to 125.5 t C ha(-1), with an average standard deviation of 50.1 +/- 12.3 t C ha(-1). The mean SOC level obtained from this survey was considerably lower than the value of 60.5 t C ha(-1) reported for the same region in the Harmonized World Soil Database (HWSD), which is the most commonly used soil database worldwide. A large spatial discrepancy of SOC stock was observed between this survey and HWSD in regional and sub-regional levels. This study provided an updated regional baseline map of SOC levels for improving farmland management and refining carbon accounting under climate change.

分类号：

  • 相关文献

[1]Modeling the impact of climate change on soil organic carbon stock in upland soils in the 21st century in China. Wan, Yunfan,Lin, Erda,Xiong, Wei,Li, Yu'e,Guo, Liping,Wan, Yunfan,Lin, Erda,Xiong, Wei,Li, Yu'e,Guo, Liping. 2011

[2]Using Machine Learning in Environmental Tax Reform Assessment for Sustainable Development: A Case Study of Hubei Province, China. Zheng, Yinger,Zheng, Yinger,Zheng, Haixia,Zheng, Haixia,Ye, Xinyue. 2016

[3]Spatiotemporal prediction of daily ambient ozone levels across China using random forest for human exposure assessment. Zhan, Yu,Di, Baofeng,Luo, Yuzhou,Grieneisen, Michael L.,Zhang, Minghua,Deng, Xunfei. 2018

[4]Determination of internal qualities of Newhall navel oranges based on NIR spectroscopy using machine learning. Liu, Cong,Yang, Simon X.,Liu, Cong,Deng, Lie.

[5]ChemBCPP: A freely available web server for calculating commonly used physicochemical properties. Dong, Jie,Wang, Ning-Ning,Zhu, Min-Feng,Zeng, Wen-Bin,Chen, Alex F.,Cao, Dong-Sheng,Liu, Ke-Yi,Chen, Alex F.,Cao, Dong-Sheng,Yun, Yong-Huan. 2017

[6]Land use and land cover change in Inner Mongolia - understanding the effects of China's re-vegetation programs. Yin, He,Pflugmacher, Dirk,Hostert, Patrick,Li, Ang,Li, Zhengguo,Hostert, Patrick. 2018

[7]A comparative study for least angle regression on NIR spectra analysis to determine internal qualities of navel oranges. Liu, Cong,Yang, Simon X.,Liu, Cong,Deng, Lie. 2015

[8]Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm. Zhan, Yu,Deng, Xunfei,Shen, Xueyou,Zhu, Lizhong,Luo, Yuzhou,Chen, Huajin,Grieneisen, Michael L.,Zhang, Minghua,Deng, Xunfei.

[9]Soil carbon sequestration under long-term rice-based cropping systems of purple soil in Southwest China. Chen Qing-rui,Qin Yu-sheng,Chen Kun,Tu Shi-hua,Xu Ming-gang,Zhang Wen-ju. 2015

[10]Crop yield and soil carbon responses to tillage method changes in North China. Tian, Shenzhong,Ning, Tangyuan,Liu, Zhen,Li, Geng,Li, Zengjia,Tian, Shenzhong,Ning, Tangyuan,Lal, Rattan,Wang, Yu.

[11]Occlusive effect of soil aggregates on increased soil DTPA-extractable zinc under low soil pH caused by long-term fertilization. Guo, Z.,Guo, X.,Wang, J.,Wang, D.,Guo, Z.,Guo, X.,Wang, J.,Wang, D.. 2013

[12]Traditional manual tillage significantly affects soil redistribution and CO2 emission in agricultural plots on the Loess Plateau. Geng, Yan,Yu, Hanqing,Tarafder, Mahbubul,Li, Yong,Tian, Guanglong,Tian, Guanglong,Chappell, Adrian. 2018

[13]Phytolith accumulation in broadleaf and conifer forests of northern China: Implications for phytolith carbon sequestration. Yang, Xiaomin,Song, Zhaoliang,Hao, Qian,Zhang, Xiaodong,Liu, Hongyan,Van Zwieten, Lukas,Song, Alin,Li, Zimin,Wang, Hailong,Wang, Hailong. 2018

[14]Water-Stable Aggregates and Associated Carbon in a Subtropical Rice Soil Under Variable Tillage. Liu, Xi-Hui,Chen, Qiu-Shi,Huang, Yan-Fei,He, Ming-Ju,Xu, Fang-Long,Li, Yang-Rui,Gu, Ming-Hua,Ou, Hui-Ping,Liu, Xi-Hui,Huang, Yan-Fei,Tan, Hong-Wei,Li, Yang-Rui. 2016

[15]Spatiotemporal variation of soil organic carbon in the cultivated soil layer of dry land in the South-Western Yunnan Plateau, China. Zhao, Ji-xia,Liu, Gang-cai,Zhao, Ji-xia,Dai, Fu-qiang,He, Shou-jia,Zhang, Qing. 2017

[16]Modeling the effects of farming management practices on soil organic carbon stock at a county-regional scale. Deng, Nanrong,Wang, Qi,Wang, Jing,Lv, Changhe,Yu, Haibin,Li, Wangjun,Chen, Zhao. 2018

[17]Characteristics of differently stabilised soil organic carbon fractions in relation to long-term fertilisation in Brown Earth of Northeast China. Xu, Xiangru,An, Tingting,Pei, Jiubo,Wang, Jingkuan,Xu, Xiangru,Zhang, Wenju,Xu, Minggang,Xiao, Jing,Xie, Hongtu. 2016

[18]Effects of Long-Term Organic Amendments on Soil Organic Carbon in a Paddy Field: A Case Study on Red Soil. Huang Qing-hai,Li Da-ming,Liu Kai-lou,Yu Xi-chu,Ye Hui-cai,Hu Hui-wen,Xu Xiao-lin,Wang Sai-lian,Zhou Li-jun,Duan Ying-hua,Zhang Wen-ju. 2014

[19]Crop residue, manure and fertilizer in dryland maize under reduced tillage in northern China: II nutrient balances and soil fertility. Wang, Xiaobin,Hoogmoed, Willem B.,Cai, Dianxiong,Perdok, Udo D.,Oenema, Oene. 2007

[20]Chemical fertilizers could be completely replaced by manure to maintain high maize yield and soil organic carbon (SOC) when SOC reaches a threshold in the Northeast China Plain. Li Hui,Feng Wen-ting,Sun Nan,Xu Ming-gang,Li Hui,Feng Wen-ting,He Xin-hua,Zhu Ping,Gao Hong-jun. 2017

作者其他论文 更多>>

微信小程序