Construction of Membership Functions for Soil Mapping using the Partial Dependence of Soil on Environmental Covariates Calculated by Random Forest

doi:10.2136/sssaj2016.06.0195

	Construction of Membership Functions for Soil Mapping using the Partial Dependence of Soil on Environmental Covariates Calculated by Random Forest
	Zeng, Canying 1,2,3; Yang, Lin 4; Zhu, A-Xing 1,2,3,4,5
刊名	SOIL SCIENCE SOCIETY OF AMERICA JOURNAL
	2017-03-01
卷号	81 期号:2 页码:341-353
ISSN号	0361-5995
DOI	10.2136/sssaj2016.06.0195
通讯作者	Yang, Lin(yanglin@lreis.ac.cn) ; Zhu, A-Xing(azhu@wisc.edu)
英文摘要	Partial dependence plots generated by Random Forest (RF) imply an association between soil and environmental variables. This study develops a method to construct membership functions representing knowledge of soil-environment relationships from partial dependence. Key parameters were obtained from normalized partial dependence to define class limits and membership gradation. Seven environmental variables were selected on the basis of the variable's importance within RF. Two cases were conducted to test the effectiveness of our method using different training samples. Case 1 used 33 representative locations as training samples and 50 locations as validations. Case 2 randomly split all 83 samples into training and validation subsets at a proportion of 2: 1; the splits were repeated seven times. For each case, the generated membership functions were used for mapping soil subgroups in Heshan, China, under the Soil Landscape Inference Model framework; RF was conducted for comparison. The results showed that mapping accuracy based on the membership functions (78%) was much higher than that of RF only (60%) in Case 1. In Case 2, the mapping accuracies using membership functions (an average of 67%, SD = 6.5%) were not always higher than those by RF (an average of 67%, SD = 8.0%). The constructed membership functions were impacted by the training samples. Use of representative training samples is recommended when applying the proposed method. However, training samples (including representative samples and other samples) with good coverage in the environmental feature space would allow RF to obtain more accurate soil maps than using representative samples.
资助项目	National Natural Science Foundation of China[41471178] ; National Natural Science Foundation of China[41431177] ; National Natural Science Foundation of China[41530749] ; Natural Science Research Program of Jiangsu[14KJA170001] ; National Key Technology Innovation Project for Water Pollution Control and Remediation[2013ZX07103006] ; cultivation project of excellent doctoral dissertations of Nanjing Normal University[YBPY16_006] ; Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD) ; Vilas Associate Award from the University of Wisconsin-Madison ; Hammel Faculty Fellow Award from the University of Wisconsin-Madison ; Manasse Chair Professorship from the University of Wisconsin-Madison ; One Thousand Talents Program of China
WOS关键词	FUZZY-LOGIC ; KNOWLEDGE DISCOVERY ; FUNCTION GENERATION ; CLASSIFICATION ; LANDSCAPE ; MODEL ; MAPS
WOS研究方向	Agriculture
语种	英语
出版者	SOIL SCI SOC AMER
WOS记录号	WOS:000400696900011
资助机构	National Natural Science Foundation of China ; Natural Science Research Program of Jiangsu ; National Key Technology Innovation Project for Water Pollution Control and Remediation ; cultivation project of excellent doctoral dissertations of Nanjing Normal University ; Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD) ; Vilas Associate Award from the University of Wisconsin-Madison ; Hammel Faculty Fellow Award from the University of Wisconsin-Madison ; Manasse Chair Professorship from the University of Wisconsin-Madison ; One Thousand Talents Program of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/62586]
专题	中国科学院地理科学与资源研究所
通讯作者	Yang, Lin; Zhu, A-Xing
作者单位	1.Nanjing Normal Univ, Minist Educ, Key Lab Virtual Geog Environm, 1 Wenyuan Rd, Nanjing 210023, Jiangsu, Peoples R China 2.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, 1 Wenyuan Rd, Nanjing 210023, Jiangsu, Peoples R China 3.State Key Lab Cultivat Base Geog Environm Evolut, Nanjing 210023, Jiangsu, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 5.Univ Wisconsin, Dept Geog, Madison, WI 53706 USA
推荐引用方式 GB/T 7714	Zeng, Canying,Yang, Lin,Zhu, A-Xing. Construction of Membership Functions for Soil Mapping using the Partial Dependence of Soil on Environmental Covariates Calculated by Random Forest[J]. SOIL SCIENCE SOCIETY OF AMERICA JOURNAL,2017,81(2):341-353.
APA	Zeng, Canying,Yang, Lin,&Zhu, A-Xing.(2017).Construction of Membership Functions for Soil Mapping using the Partial Dependence of Soil on Environmental Covariates Calculated by Random Forest.SOIL SCIENCE SOCIETY OF AMERICA JOURNAL,81(2),341-353.
MLA	Zeng, Canying,et al."Construction of Membership Functions for Soil Mapping using the Partial Dependence of Soil on Environmental Covariates Calculated by Random Forest".SOIL SCIENCE SOCIETY OF AMERICA JOURNAL 81.2(2017):341-353.