您好，欢迎访问中国热带农业科学院 机构知识库！
中国热带农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Digital mapping of soil organic matter for rubber plantation at regional scale: An application of random forest plus residuals kriging approach

文献类型： 外文期刊

作者： Guo, Peng-Tao 1 ; Li, Mao-Fen 2 ; Luo, Wei 1 ; Tang, Qun-Feng 3 ; Liu, Zhi-Wei 3 ; Lin, Zhao-Mu 1 ;

作者机构： 1.Chinese Acad Trop Agr Sci, Rubber Res Inst, Danzhou 571737, Hainan, Peoples R China

2.Southwest Univ, Coll Resources & Environm, Chongqing 400716, Peoples R China

3.Hainan Agr Reclamat Acad Sci, Haikou 570206, Peoples R China

关键词： Environmental variable;Rubber tree;Tropical area;Predictive soil mapping

期刊名称：GEODERMA （ 影响因子：6.114； 五年影响因子：6.183 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： Soil organic matter (SOM) plays an important role in soil fertility and C cycle. Detailed information about the spatial distribution of SUM is vital to effective management of soil fertility and better understanding of the process of C cycle. To date, however, few studies have been carried out to digitally map the spatial variation of SUM for rubber (Hevea brasiliensis) plantation at the regional scale in Hainan Island, China. In this study, a hybrid approach, random forest plus residuals kriging (RFRK), was proposed to predict and map the spatial pattern of SUM for the rubber plantation. A total of 2511 topsoil (0-20 cm) samples were extracted from a soil fertility survey data set of the Danzhou County. These soil samples were randomly divided into calibration dataset (1757 soil samples) and validation dataset (754 soil samples). In this study, stepwise linear regression (SLR), random forest (RF), and random forest plus residuals kriging (RFRK) were used to predict and map the spatial distribution of SUM for the rubber plantation, while generalized additive mixed model (GAMM) and classification and regression tree (CART) were employed to uncover relationships between SUM and environmental variables and further to identify the main factors influencing SUM variation. The RFRK model was developed to predict spatial variability of SUM on the basis of terrain attributes, geological units, climate factors, and vegetation index. Performance of RFRK was compared with SLR. Mean error (ME), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R-2) were selected as comparison criteria. Results showed that RFRK performed much better than SLR in predicting and mapping the spatial distribution of SUM for the rubber plantation. The RFRK model had much lower prediction errors (ME, MAE, and RMSE) and higher R-2 than SLR. Values of ME, MAE, RMSE, and R-2 were 026 g/kg, 135 g/kg, 2.19 g/kg, and 0.86 for RFRK model, and were 0.65 g/kg, 2.99 g/kg, 437 g/kg, and 0.43 for SLR equation, respectively. Moreover, RFRK model yielded a more realistic spatial distribution of SUM than SLR equation. The good performance of RFRK model could be ascribed to its capabilities of dealing with non-linear and hierarchical relationships between SUM and environmental variables and of accounting for unexplained information in the random forest (RF) model residuals. These results suggested that RFRK was a promising approach in predicting spatial distribution of SUM for rubber plantation at regional scale. (C) 2014 Elsevier B.V. All rights reserved.

  • 相关文献

[1]橡胶树炭疽病菌Cap2移基因的克隆和序列分析. 林春花,李超萍,李博勋,周维,黄贵修. 2012

[2]De novo assembly and characterization of bark transcriptome using Illumina sequencing and development of EST-SSR markers in rubber tree (Hevea brasiliensis Muell. Arg.). Li, Dejun,Deng, Zhi,Qin, Bi,Liu, Xianghong,Men, Zhonghua. 2012

[3]Design of natural rubber precision ditch fertilization machine. Wang, Yeqin,Deng, Yiguo,Zhang, Yuan,Wei, Lijiao. 2017

[4]Gain-of-function in Arabidopsis (GAINA) for identifying functional genes in Hevea brasiliensis. Cheng, Han,Gao, Jing,Cai, Haibin,Zhu, Jianshun,Huang, Huasun,Cheng, Han,Huang, Huasun. 2016

[5]Molecular mechanism of ethylene stimulation of latex yield in rubber tree (Hevea brasiliensis) revealed by de novo sequencing and transcriptome analysis. Liu, Jin-Ping,Zhuang, Yu-Fen,Guo, Xiu-Li,Li, Yi-Jian. 2016

[6]Identification of novel microRNAs in Hevea brasiliensis and computational prediction of their targets. Gebelin, Virginie,Argout, Xavier,Engchuan, Worrawat,Pitollat, Bertrand,Duan, Cuifang,Montoro, Pascal,Leclercq, Julie,Engchuan, Worrawat,Duan, Cuifang. 2012

[7]Transcriptome sequencing and analysis of rubber tree (Hevea brasiliensis Muell.) to discover putative genes associated with tapping panel dryness (TPD). Liu, Jin-Ping,Tian, Xiao-Yan,Xia, Zhi-Qiang,Li, Yi-Jian. 2015

[8]Characterization of HbEREBP1, a wound-responsive transcription factor gene in laticifers of Hevea brasiliensis Muell. Arg.. Chen, Yue-Yi,Wang, Li-Feng,Dai, Long-Jun,Yang, Shu-Guang,Tian, Wei-Min,Chen, Yue-Yi.

[9]The small RNA profile in latex from Hevea brasiliensis trees is affected by tapping panel dryness. Gebelin, Virginie,Leclercq, Julie,Argout, Xavier,Sarah, Gautier,Montoro, Pascal,Kuswanhadi,Chaidamsari, Tetty,Hu, Songnian,Yang, Meng,Tang, Chaorong. 2013

[10]Ultrasound-assisted tapping of latex from Para rubber tree Hevea brasiliensis. She, Fenghua,Wang, Jin,An, Feng,Lin, Weifu,Zhu, Deming,She, Fenghua,Kong, Lingxue,An, Feng. 2013

[11]Characterization of Sugar Contents and Sucrose Metabolizing Enzymes in Developing Leaves of Hevea brasiliensis. Zhu, Jinheng,Qi, Jiyan,Fang, Yongjun,Xiao, Xiaohu,Lan, Jixian,Tang, Chaorong,Zhu, Jinheng,Lan, Jixian,Tang, Chaorong,Li, Jiuhui. 2018

[12]Next-generation sequencing, assembly, and comparative analyses of the latex transcriptomes from two elite Hevea brasiliensis varieties. Li, Dejun,Liu, Hui,Zhao, Manman,Deng, Zhi,Li, Yu,Zeng, Rizhong,Tian, Weimin,Hao, Lili,Zhao, Manman. 2015

[13]Proteome analysis of interaction between rootstocks and scions in Hevea brasiliensis. Yuan, Kun,Yang, Li-Fu,Wang, Zhen-Hui,Lin, Wei-Fu,Cao, Jian-Hua,Yuan, Kun,Yang, Li-Fu,Wang, Zhen-Hui,Lin, Wei-Fu,Cao, Jian-Hua,Ding, Xuan. 2011

[14]Regulation of MIR Genes in Response to Abiotic Stress in Hevea brasiliensis. Gebelin, Virginie,Leclercq, Julie,Montoro, Pascal,Hu, Songnian,Tang, Chaorong. 2013

[15]Identification, Functional Study, and Promoter Analysis of HbMFT1, a Homolog of MFT from Rubber Tree (Hevea brasiliensis). Bi, Zhenghong,Bi, Zhenghong,Huang, Huasun,Hua, Yuwei,Li, Xiang. 2016

[16]Molecular cloning and characterization of S-adenosylmethionine decarboxylase gene in rubber tree (Hevea brasiliensis). Zhao, Manman,Liu, Hui,Deng, Zhi,Chen, Jiangshu,Yang, Hong,Li, Dejun,Zhao, Manman,Li, Huiping,Xia, Zhihui.

[17]Development, characterization, genetic diversity and cross-species/genera transferability of ILP markers in rubber tree (Hevea brasiliensis). Li, Dejun,Deng, Zhi,Xia, Zhihui,Liu, Xianghong,Feng, Fuying.

[18]Identification of genes differentially expressed in the roots of rubber tree (Hevea brasiliensis Muell. Arg.) in response to phosphorus deficiency. He, Peng,Qin, Huaide,Wu, Min,Wu, Bingsun,Wei, Jiashao,Wang, Dapeng.

[19]Development and characterization of intron-flanking EST-PCR markers in rubber tree (Hevea brasiliensis Muell. Arg.). Li, Dejun,Deng, Zhi,Liu, Xianghong,Xia, Zhihui,Dong, Junmei,Feng, Fuying.

[20]Cloning and characterization of HbMT2a, a metallothionein gene from Hevea brasiliensis Muell. Arg differently responds to abiotic stress and heavy metals. Li, Yan,Chen, Yue Yi,Yang, Shu Guang,Tian, Wei Min.

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：中国热带农业科学院

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