气候变化领域集成服务门户(CCPortal): Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed

CCPortal

DOI	10.1016/j.jag.2019.01.002
	Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed
	Waldner F.; Bellemans N.; Hochman Z.; Newby T.; de Abelleyra D.; Verón S.R.; Bartalev S.; Lavreniuk M.; Kussul N.; Maire G.L.; Simoes M.; Skakun S.; Defourny P.
发表日期	2019
ISSN	15698432
起始页码	82
结束页码	93
卷号	80
英文摘要	Cropland maps derived from satellite imagery have become a common source of information to estimate food production, support land use policies, and measure the environmental impacts of agriculture. Cropland classification models are typically calibrated with data collected from roadside surveys which enable the sampling of large areas at a relatively low cost. However, there is a risk of providing biased data as environmental and management gradients may not be fully captured from road networks, thereby violating the assumption of representativeness of calibration data. Despite being widely adopted, the potential biases of roadside sampling have so far not been thoroughly addressed. In this study, we looked for evidence of these biases by comparing three sampling strategies: Random sampling, Roadside sampling, and Transect sampling – a spatially constrained variant of Roadside sampling. In these three strategies, non-cropland data are randomly distributed as they can be photo-interpreted. Based on reference maps at 30 m in four study sites, we followed a Monte Carlo approach to generate multiple realizations of each sampling strategy for ten sample sizes. The effect of the sampling strategy was then assessed in terms of representativeness of the data set collected and accuracy of the resulting maps. Results showed that data sets obtained from Roadside sampling were significantly less representative than those obtained from Random sampling but the resulting maps were only marginally less accurate (2% difference). Transect sampling captured systematically less variability than Random or Roadside sampling which led to differences in accuracy as large as 15%. The effect of sample size on accuracy varied across sites but generally leveled off after reaching 3000 pixels. Augmenting the size of Transect samples improved the classification accuracy but not sufficiently to match the performance of the other sampling strategies. Finally, we found that Random and Roadside training sets with similar representativeness yield comparable accuracy. Therefore, we conclude that roadside sampling can be a viable source of training data for cropland mapping if the range of environmental and management gradients is surveyed. This underlines the importance of survey planning to identify those routes that capture most variability. © 2019 Elsevier B.V.
英文关键词	Accuracy; Agriculture; Classification; Representativeness; Sample size; Sampling
语种	英语
scopus关键词	accuracy assessment; agricultural land; agricultural management; data set; environmental gradient; land classification; mapping; roadside environment; sampling; survey
来源期刊	International Journal of Applied Earth Observation and Geoinformation
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/156456
作者单位	CSIRO Agriculture & Food, Queensland Bioscience Precinct, 306 Carmody Road, St Lucia, QLD 4067, Australia; Université catholique de Louvain, Earth and Life Institute - Environment, Croix du Sud, Louvain-la-Neuve, Belgium; Agricultural Research Council, Private Bag X79, Pretoria, 0001, South Africa; Instituto de Clima y Agua, Instituto Nacional de Tecnología Agropecuaria (INTA), Argentina; Space Research Institute of Russian Academy of Sciences (IKI), Moscow, Russian Federation; Space Research Institute NAS and SSA (SRI), Kyiv, Ukraine; CIRAD, UMR Eco &Sols, Campinas, Brazil; Eco &Sols, Univ Montpellier, CIRAD, INRA, IRD, Montpellier SupAgro, Montpellier, France; Interdisciplinary Center of Energy Planning (NIPE), UNICAMP, Campinas, 13083-896, Brazil; Brazilian Bioethanol Science and Technology Laboratory (CTBE), Brazilian Research Center in Energy and Materials (CNPEM), Campinas, 13083-970, Brazil; Rio de Janeiro State University (UERJ), Rua São Francisco Xavier, 524, Maracanã, Rio de Janeiro, RJ 20550-...
推荐引用方式 GB/T 7714	Waldner F.,Bellemans N.,Hochman Z.,et al. Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed[J],2019,80.
APA	Waldner F..,Bellemans N..,Hochman Z..,Newby T..,de Abelleyra D..,...&Defourny P..(2019).Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed.International Journal of Applied Earth Observation and Geoinformation,80.
MLA	Waldner F.,et al."Roadside collection of training data for cropland mapping is viable when environmental and management gradients are surveyed".International Journal of Applied Earth Observation and Geoinformation 80(2019).