干旱区生态环境知识资源中心(Arid): CCropLand30: High-resolution hybrid cropland maps of China created through the synergy of state-of-the-art remote sensing products and the latest national land survey

Arid

DOI	10.1016/j.compag.2024.108672
	CCropLand30: High-resolution hybrid cropland maps of China created through the synergy of state-of-the-art remote sensing products and the latest national land survey
	Zhang, Ling; Wang, Weiguo; Ma, Qimin; Hu, Yingyi; Ma, Hui; Zhao, Yanbo
通讯作者	Zhang, L
来源期刊	COMPUTERS AND ELECTRONICS IN AGRICULTURE
ISSN	0168-1699
EISSN	1872-7107
出版年	2024
卷号	218
英文摘要	Accurate information on the extents and dynamics of croplands is crucial to address the twin challenges of meeting the growing food needs while reducing environmental footprint. Despite the availability of numerous global and regional cropland maps, significant uncertainties and discrepancies persist in terms of overall area and spatial distribution. In this study, we developed high-resolution hybrid cropland maps of China (CCropLand30) by integrating state-of-the-art remote sensing land use and land cover products (i.e., GlobeLand30, GLAD, CLUD, CLCD, and CACD) with the latest national land survey (NLDS). To this end, we proposed a cost-effective datafusion approach, namely the majority voting-fuzzy agreement score (MV-FAS) method. The accuracy of CCropLand30 and the input cropland maps was evaluated using both visually interpreted and third-party samples, along with county-level NLDS data. CCropLand30 attains an overall accuracy, Kappa coefficient, and F1score of 0.88, 0.76, and 0.86, respectively, for the year circa 2020. It demonstrates better agreement with the reference points compared to the input cropland maps, resulting in an enhancement in overall accuracy ranging 10-30%. Moreover, CCropLand30 shows superior spatial consistency with the NLDS data, achieving an average improvement in spatial pattern efficiency by 25%. The superiority of CCropLand30 was further confirmed by regional visual comparison of the cropland maps. The CCropLand30 product reveals a clear decreasing trend in China's cropland area from 2000 to 2020. The area of cropland reduced significantly in relatively waterabundant regions but expanded notably in arid and semi-arid regions with scarce water resources, raising concerns about the spatial mismatch between water and land resources in China. Our high-resolution hybrid cropland product, CCropLand30, will provide substantial support for cropland monitoring and management, as well as research in diverse fields.
英文关键词	Hybrid cropland map Land use and land cover products Data fusion National land survey Spatial pattern efficiency Food security China
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:001177606200001
WOS关键词	GLOBAL CROPLAND ; OPEN-ACCESS ; COVER ; INTEGRATION ; EXTENT
WOS类目	Agriculture, Multidisciplinary ; Computer Science, Interdisciplinary Applications
WOS研究方向	Agriculture ; Computer Science
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/403250
推荐引用方式 GB/T 7714	Zhang, Ling,Wang, Weiguo,Ma, Qimin,et al. CCropLand30: High-resolution hybrid cropland maps of China created through the synergy of state-of-the-art remote sensing products and the latest national land survey[J],2024,218.
APA	Zhang, Ling,Wang, Weiguo,Ma, Qimin,Hu, Yingyi,Ma, Hui,&Zhao, Yanbo.(2024).CCropLand30: High-resolution hybrid cropland maps of China created through the synergy of state-of-the-art remote sensing products and the latest national land survey.COMPUTERS AND ELECTRONICS IN AGRICULTURE,218.
MLA	Zhang, Ling,et al."CCropLand30: High-resolution hybrid cropland maps of China created through the synergy of state-of-the-art remote sensing products and the latest national land survey".COMPUTERS AND ELECTRONICS IN AGRICULTURE 218(2024).