您好，欢迎访问江苏省农业科学院 机构知识库！
江苏省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Prediction of soil organic carbon in an intensively managed reclamation zone of eastern China: A comparison of multiple linear regressions and the random forest model

文献类型： 外文期刊

作者： Zhang, Huan 1 ; Wu, Pengbao 1 ; Yin, Aijing 2 ; Yang, Xiaohui 1 ; Zhang, Ming 3 ; Gao, Chao 1 ;

作者机构： 1.Nanjing Univ, Sch Geog & Oceanog Sci, Nanjing 210023, Jiangsu, Peoples R China

2.Jiangsu Acad Agr Sci, Inst Agr Resources & Environm, Nanjing 210014, Jiangsu, Peoples R China

3.China Geol Survey, Nanjing Ctr, Nanjing 210000, Jiangsu, Peoples R China

关键词： Soil organic carbon;Random Forest;Factor importance;Reclaimed soils

期刊名称：SCIENCE OF THE TOTAL ENVIRONMENT （ 影响因子：7.963； 五年影响因子：7.842 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： Organic carbon is a key component of soils and plays a fundamental role in soil fertility and climate change. Determining the importance of potential drivers of soil organic carbon (SOC) and thus predicting the distribution of SOC are important formeasuring carbon sequestration oremissions. Coastalwetlands are precious land resources that are currently undergoing rapid reclamation in China. The alternations in soil physicochemical conditions caused by reclamation can strongly impact the cycle of organic carbon. However, identification of the important drivers of SOC dynamics and prediction of SOC using the potential drivers remain largely unclear. In this study, we used classification and regression tree (CART) to identify the importance of the potential drivers of SOC at 241 sites from an intensively managed reclamation zone of eastern China. Multiple linear regressions (MLR) and random forest (RF) models were applied to predict the distribution of SOC using continuous variables, such as the contents of Cl, CaO, Fe2O3, Al2O3, SiO2, clay, silt, and sand aswell as the soil pH, alongwith categorical variables, such as land use and reclamation duration. The results indicate that the soil/sediment pH was the most important variable impacting SOC, followed by the Cl and silt contents. The RF and MLR involving all predictor variables produced much higher R-2 and lower error indices than the RF and MLRmodels involving independent variables (pH and CaO). RF performed much better than MLR as it revealed much lower error indices (ME, MSE, and RMSE) and a higher R-2 than MLR. The superiority of RF in predicting SOC is related to its capability to deal with non-linear and hierarchical relationships between SOC and predictors. Analyses of land use effects on SOC dynamics indicated that paddy soils were superior in sequestering SOC than other land use types, which is likely ascribed to the rapid desalination and dealkalization of paddy field management. Therefore, paddy field management is recommended as an environment-friendly approach for managing newly reclaimed lands. (C) 2017 Elsevier B.V. All rights reserved.

  • 相关文献

[1]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.

[2]Spatial distributions of soil chemical and physical properties prior to planting soybean in soil under ridge-, no- and conventional-tillage in a maize-soybean rotation. Fan, R. Q.,Fan, R. Q.,Yang, X. M.,Drury, C. F.,Reynolds, W. D.,Fan, R. Q.,Zhang, P..

[3]The trend of soil organic carbon, total nitrogen, and wheat and maize productivity under different long-term fertilizations in the upland fluvo-aquic soil of North China. Yang, Jun,Ren, Shun-rong,Liu Hailong.

[4]Long-term effects of fertilizer managements on crop yields and organic carbon storage of a typical rice-wheat agroecosystem of China. Yang, Lin-Zhang,Yao, Yue-Ming,Wu, Dong-Dong,Wang, Jianguo,Guo, Ruli,Yin, Shixue. 2007

作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：江苏省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台