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

第一作者： Guo, Peng-Tao

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

作者机构：

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.

分类号： S15

  • 相关文献

[1]Monthly Variation in Crustacean Assemblage (Decapod and Stomatopod) and Its Relationships with Environmental Variables in Laizhou Bay, China. Wu Qiang,Wu Qiang,Wang Jun,Zhang Bo,Chen Ruisheng,Jin Xianshi,Wang Jun,Zhang Bo,Jin Xianshi. 2016

[2]Modeling and mapping of cadmium in soils based on qualitative and quantitative auxiliary variables in a cadmium contaminated area. Cao, Shanshan,Lu, Anxiang,Wang, Jihua,Cao, Shanshan,Lu, Anxiang,Wang, Jihua,Lu, Anxiang,Huo, Lili.

[3]Annual dynamics of the abundance of fish larvae and its relationship with hydrological variation in the Pearl River. Tan, Xichang,Li, Xinhui,Li, Yuefei,Wang, Chao,Li, Jie,Luo, Jianren,Lek, Sovan.

[4]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

[5]Rubber Trees Demonstrate a Clear Retranslocation Under Seasonal Drought and Cold Stresses. Li, Yuwu,Li, Yuwu,Lan, Guoyu,Xia, Yujie. 2016

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

[7]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

[8]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

[9]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

[10]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

[11]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.

[12]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

[13]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

[14]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

[15]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

[16]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

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

[18]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

[19]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.

[20]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.

作者其他论文 更多>>

微信小程序