气候变化领域集成服务门户(CCPortal): Comparing map-based and library-based training approaches for urban land-cover fraction mapping from Sentinel-2 imagery

CCPortal

DOI	10.1016/j.jag.2019.02.003
	Comparing map-based and library-based training approaches for urban land-cover fraction mapping from Sentinel-2 imagery
	Priem F.; Okujeni A.; van der Linden S.; Canters F.
发表日期	2019
ISSN	15698432
起始页码	295
结束页码	305
卷号	78
英文摘要	An improved trade-off between resolution, coverage and revisit time, makes Sentinel-2 multispectral imagery an interesting data source for mapping the composition and spatial-temporal dynamics of urban land cover. To fully realize the potential of Sentinel-2′s high amount of available data, efficient urban mapping workflows are required. Machine learning regression is a powerful approach to produce subpixel land cover fractions from remote sensing imagery, yet it requires mixed spectra for model training for which the fractions of the land cover classes present in the pixel are known. Typically, this data is obtained by sampling spectra from the image to be unmixed, and corresponding land-cover fractions from higher-resolution land cover reference data, i.e. map-based training. We propose synthetic mixing of library spectra as an alternative for producing land cover fraction training data for regression modelling, i.e. library-based training. The approach is applied to a Sentinel-2 image of the city of Brussels (Belgium) and part of its urban fringe for mapping Vegetation, Impervious, and Soil (VIS) fractions at 20 m resolution. VIS fraction maps obtained with library-based training have mean absolute errors below 0.1 for all three surface types. The composition of these three key surface categories and their spatial distribution is well represented for the entire area in resulting maps. As a proof of concept, library-based training is compared with the map-based training approach. The more flexible library-based training not only achieves similar mapping accuracies, but in most cases, outperforms the map-based training approach in terms of bias and magnitude of error. The outcome of the research suggests that use of spectral libraries and synthetic mixing may provide an efficient modelling framework for regression-based mapping from Sentinel-2 imagery in operational contexts. © 2019 Elsevier B.V.
英文关键词	Brussels; Regression; Sentinel-2; Spectral libraries; Support vector machine; Synthetic mixing; Urban
语种	英语
scopus关键词	image processing; land cover; regression analysis; Sentinel; spectral resolution; support vector machine; urban area; vegetation mapping; Belgium; Brussels [Belgium]; Brussels [Brussels (RGA)]
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/156477
作者单位	Cartography and GIS Research Group, Vrije Universiteit Brussel, Belgium; Geography Department, Humboldt-Universität zu Berlin, Germany
推荐引用方式 GB/T 7714	Priem F.,Okujeni A.,van der Linden S.,et al. Comparing map-based and library-based training approaches for urban land-cover fraction mapping from Sentinel-2 imagery[J],2019,78.
APA	Priem F.,Okujeni A.,van der Linden S.,&Canters F..(2019).Comparing map-based and library-based training approaches for urban land-cover fraction mapping from Sentinel-2 imagery.International Journal of Applied Earth Observation and Geoinformation,78.
MLA	Priem F.,et al."Comparing map-based and library-based training approaches for urban land-cover fraction mapping from Sentinel-2 imagery".International Journal of Applied Earth Observation and Geoinformation 78(2019).