Updating land cover automatically based on change detection using satellite images: case study of national forests in Southern California

doi:10.1080/15481603.2017.1286727

	Updating land cover automatically based on change detection using satellite images: case study of national forests in Southern California
	Huang, Shengli 1; Ramirez, Carlos 1; Kennedy, Kama 1; Mallory, Jeffrey 1; Wang, Juanle 2; Chu, Christine 3
刊名	GISCIENCE & REMOTE SENSING
	2017
卷号	54 期号:4 页码:495-514
关键词	land cover update time series images change detection remote sensing
ISSN号	1548-1603
DOI	10.1080/15481603.2017.1286727
通讯作者	Huang, Shengli(shenglihuang@fs.fed.us)
英文摘要	Observing dynamic change patterns and higher-order complexities from remotely sensed images is warranted, but the main challenges include image inconsistency, plant phenological differences, weather variations, and difficulties of incorporating natural conditions into automatic image processing. In this study, we proposed a new algorithm and demonstrated it by producing 2002-2008 and 2010 land-cover maps in heterogeneous Southern California based on an existing 2009 land-cover map. The new algorithm improves the baseline land-cover map quality by discarding potential bad land-cover pixels and dividing each land-cover type into several subclasses. Time series Landsat images were used to detect changed and unchanged areas between baseline year and target year t. Subsequently, for each individual year t, each pixel that was identified as unchanged inherited the baseline classification. Otherwise, each pixel in the changed areas was classified by a similar surrogate majority classifier. The demonstration results in Southern California showed that the land-cover temporal pattern captured the observed successional stages of the ecosystem very well. The accuracy assessment had an overall classification accuracies ranging from 81% to 86% and overall kappa coefficients ranging from 0.79 to 0.83.
资助项目	United States Department of Agriculture (USDA), Forest Service, Forest Health Monitoring Program
WOS关键词	CLASSIFICATION ; GENERATION ; INVENTORY ; SYSTEM ; MAPS ; USA
WOS研究方向	Physical Geography ; Remote Sensing
语种	英语
出版者	TAYLOR & FRANCIS LTD
WOS记录号	WOS:000401522100003
资助机构	United States Department of Agriculture (USDA), Forest Service, Forest Health Monitoring Program
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/64452]
专题	中国科学院地理科学与资源研究所
通讯作者	Huang, Shengli
作者单位	1.US Forest Serv, USDA, Informat Management, Remote Sensing Lab, Reg 5,3237 Peacekeeper Way,Suite 201, Mcclellan, CA 95652 USA 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, 11A,Datun Rd, Beijing 100101, Peoples R China 3.10811 US Forest Serv, Tahoe Natl Forest, Truckee, CA 96161 USA
推荐引用方式 GB/T 7714	Huang, Shengli,Ramirez, Carlos,Kennedy, Kama,et al. Updating land cover automatically based on change detection using satellite images: case study of national forests in Southern California[J]. GISCIENCE & REMOTE SENSING,2017,54(4):495-514.
APA	Huang, Shengli,Ramirez, Carlos,Kennedy, Kama,Mallory, Jeffrey,Wang, Juanle,&Chu, Christine.(2017).Updating land cover automatically based on change detection using satellite images: case study of national forests in Southern California.GISCIENCE & REMOTE SENSING,54(4),495-514.
MLA	Huang, Shengli,et al."Updating land cover automatically based on change detection using satellite images: case study of national forests in Southern California".GISCIENCE & REMOTE SENSING 54.4(2017):495-514.