Predictive mapping with small field sample data using semi-supervised machine learning

doi:10.1111/tgis.12598

	Predictive mapping with small field sample data using semi-supervised machine learning
	Du, Fei 2; Zhu, A-Xing 2,3,4,5; Liu, Jing 1; Yang, Lin 6
刊名	TRANSACTIONS IN GIS
	2019-12-04
页码	17
ISSN号	1361-1682
DOI	10.1111/tgis.12598
通讯作者	Zhu, A-Xing(azhu@wisc.edu)
英文摘要	Existing predictive mapping methods usually require a large number of field samples with good representativeness as input to build reliable predictive models. In mapping practice, however, we often face situations when only small sample data are available. In this article, we present a semi-supervised machine learning approach for predictive mapping in which the natural aggregation (clustering) patterns of environmental covariate data are used to supplement limited samples in prediction. This approach was applied to two soil mapping case studies. Compared with field sample only approaches (decision trees, logistic regression, and support vector machines), maps using the proposed approach can better capture the spatial variation of soil types and achieve higher accuracy with limited samples. A cross validation shows further that the proposed approach is less sensitive to the specific field sample set used and thus more robust when field sample data are small.
资助项目	PAPD ; Outstanding Innovation Team in Colleges and Universities in Jiangsu Province ; National Natural Science Foundation of China[41431177] ; National Natural Science Foundation of China[41871300] ; National Basic Research Program of China[2015CB954102]
WOS关键词	MARKOV-CHAIN ALGORITHM ; SPATIAL PREDICTION ; SOIL-LANDSCAPE ; CLASSIFICATION ; KNOWLEDGE ; VARIABLES ; MODEL ; SIZE ; TREE ; GIS
WOS研究方向	Geography
语种	英语
出版者	WILEY
WOS记录号	WOS:000500536400001
资助机构	PAPD ; Outstanding Innovation Team in Colleges and Universities in Jiangsu Province ; National Natural Science Foundation of China ; National Basic Research Program of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/130292]
专题	中国科学院地理科学与资源研究所
通讯作者	Zhu, A-Xing
作者单位	1.Santa Monica Coll, Santa Monica, CA USA 2.Univ Wisconsin, Dept Geog, 550 North Pk St, Madison, WI 53706 USA 3.Nanjing Normal Univ, Sch Geog Sci, Nanjing, Jiangsu, Peoples R China 4.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing, Jiangsu, Peoples R China 5.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China 6.Nanjing Univ, Sch Geog & Oceanog Sci, Nanjing, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Du, Fei,Zhu, A-Xing,Liu, Jing,et al. Predictive mapping with small field sample data using semi-supervised machine learning[J]. TRANSACTIONS IN GIS,2019:17.
APA	Du, Fei,Zhu, A-Xing,Liu, Jing,&Yang, Lin.(2019).Predictive mapping with small field sample data using semi-supervised machine learning.TRANSACTIONS IN GIS,17.
MLA	Du, Fei,et al."Predictive mapping with small field sample data using semi-supervised machine learning".TRANSACTIONS IN GIS (2019):17.