Evaluation of conditioned Latin hypercube sampling for soil mapping based on a machine learning method

doi:10.1016/j.geoderma.2020.114337

	Evaluation of conditioned Latin hypercube sampling for soil mapping based on a machine learning method
	Yang, Lin 1,6; Li, Xinming 1,7; Shi, Jingjing 1; Shen, Feixue 6; Qi, Feng 5; Gao, Binbo 4; Chen, Ziyue 3; Zhu, A-Xing 1,2,7; Zhou, Chenghu 1,6
刊名	GEODERMA
	2020-06-15
卷号	369 页码:15
关键词	Conditioned Latin hypercube sampling Soil mapping Representativeness Sample randomness
ISSN号	0016-7061
DOI	10.1016/j.geoderma.2020.114337
通讯作者	Chen, Ziyue(zychen@bnu.edu.cn)
英文摘要	Sampling design plays an important role in soil survey and soil mapping. Conditioned Latin hypercube sampling (cLHS) has been proven as an efficient sampling strategy and used widely in digital soil mapping. cLHS samples are randomly selected in each stratum of environmental variables, thus the produced sample sets can vary significantly at different runs with the same sample size. Although variation of mapping accuracies caused by the randomness of cLHS has been realized and qualitatively mentioned in past studies. However, how the randomness of cLHS could quantitatively influence mapping accuracy has rarely been examined. In this study, we conducted experiments to examine how the sample randomness quantitatively influence soil mapping accuracy with different sample sizes, and analyzed the possible reasons from a pedogenesis perspective. The results showed that the largest range of mapping accuracies of 500 repeats was 39.5% at a sample density of 2.59 point/ km(2), while the smallest range was 7.3% at the maximum sample size with a sample density of 32.47 point/km(2). The sample density for satisfactory prediction accuracies in our study area was at least 10.06 Point/km(2). The results showed that both the allocation of sample points to each soil series and the typicality of sample points played important roles in mapping accuracies. But the deep reasons causing the unstable performance of cLHS at small sample sizes were the imbalanced class distribution of soil series and the overlap between soil series in the distribution of environmental covariates. Researchers need to be cautious about the output when applying cLHS with small sampling densities. Some effective approaches to address this issue include increasing the sample size, checking the sample allocations of a cLHS design with the assistance of legacy soil maps, or adding the legacy soil map as a variable during sampling design. When the sampling resources and legacy soil maps are limited for an area, fuzzy k-means clustering sampling could be a potential alternative. This study provides useful references for better understanding the uncertainty of cLHS when the sample density is small and selecting alternative sampling methods accordingly.
资助项目	National Natural Science Foundation of China[41971054] ; National Natural Science Foundation of China[41530749] ; Leading Funds for the First class Universities[020914912203] ; Leading Funds for the First class Universities[020914902302]
WOS关键词	RANDOM FORESTS ; DESIGN ; MODEL ; CLASSIFICATION ; PREDICTION ; STOCKS ; OPTIMIZATION ; VARIABILITY ; VALIDATION ; REGRESSION
WOS研究方向	Agriculture
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000524458800004
资助机构	National Natural Science Foundation of China ; Leading Funds for the First class Universities
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/133859]
专题	中国科学院地理科学与资源研究所
通讯作者	Chen, Ziyue
作者单位	1.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Nanjing Normal Univ, Key Lab Virtual Geog Environm, Minist Educ, Nanjing 210023, Peoples R China 3.Beijing Normal Univ, Coll Global Change & Earth Syst Sci, 19 Xinjiekouwai St, Beijing 100083, Peoples R China 4.China Agr Univ, Coll Land Sci & Technol, Tsinghua East Rd, Beijing 100083, Peoples R China 5.Kean Univ, Sch Environm & Sustainabil Sci, Union, NJ 07083 USA 6.Nanjing Univ, Sch Geog & Ocean Sci, Nanjing 210023, Peoples R China 7.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Yang, Lin,Li, Xinming,Shi, Jingjing,et al. Evaluation of conditioned Latin hypercube sampling for soil mapping based on a machine learning method[J]. GEODERMA,2020,369:15.
APA	Yang, Lin.,Li, Xinming.,Shi, Jingjing.,Shen, Feixue.,Qi, Feng.,...&Zhou, Chenghu.(2020).Evaluation of conditioned Latin hypercube sampling for soil mapping based on a machine learning method.GEODERMA,369,15.
MLA	Yang, Lin,et al."Evaluation of conditioned Latin hypercube sampling for soil mapping based on a machine learning method".GEODERMA 369(2020):15.