干旱区生态环境知识资源中心(Arid): Automated training sample definition for seasonal burned area mapping

Arid

DOI	10.1016/j.isprsjprs.2019.11.026
	Automated training sample definition for seasonal burned area mapping
	Malambo, Lonesome 1; Heatwole, Conrad D.2
通讯作者	Malambo, Lonesome
来源期刊	ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
ISSN	0924-2716
EISSN	1872-8235
出版年	2020
卷号	160 页码:107-123
英文摘要	Monitoring of environmental change can benefit from the increasing availability of multitemporal satellite imagery, and efficient and effective analysis tools are needed to generate relevant spatio-temporal land cover datasets. We present a data driven approach for automatic training sample selection to support supervised spatio-temporal mapping of seasonally burned areas in the semi-arid savannas of Southern Africa. Our approach leveraged the distinctive spectral-temporal trajectories associated with areas on the landscape burned at different times or areas remaining unburned over time. Using fuzzy c-means clustering, we extracted distinctive trajectories from the multitemporal mid-infrared burn index (MIRBI) data derived from Landsat data and characterized them based on empirically developed labeling rules. The selected training trajectories captured both the bum condition (burned or unburned) and if burned, the timeframe of the burn event. We assessed the approach by training a Random Forests model using over 2500 automatically selected training data and validated the model against ground truth for years 2009 and 2014. Based on over 1000 validation points in each year, we obtained overall accuracies above 90% showing reliable and consistent training data were supplied by our automatic training sample selection approach. The method provides a data driven and automatic approach which can reduce the time-consuming and expensive training task, enabling quicker generation of relevant burned area information that can support fire monitoring programs and climate change research.
英文关键词	Fire Burned area Automatic training Abrupt change Clustering Fuzzy c-means Landsat Random Forest Zambia Southern Africa
类型	Article
语种	英语
国家	USA
收录类别	SCI-E
WOS记录号	WOS:000510525500008
WOS关键词	FUZZY C-MEANS ; LANDSAT TIME-SERIES ; SURFACE REFLECTANCE ; MAXIMUM-LIKELIHOOD ; FOREST DISTURBANCE ; SPECTRAL INDEXES ; FIRE REGIMES ; ETM PLUS ; CLASSIFICATION ; ALGORITHM
WOS类目	Geography, Physical ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Physical Geography ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/314830
作者单位	1.Texas A&M Univ, Dept Ecosyst Sci & Management, College Stn, TX 77843 USA; 2.Virginia Polytech & State Univ, Dept Biol Syst Engn, Blacksburg, VA 24061 USA
推荐引用方式 GB/T 7714	Malambo, Lonesome,Heatwole, Conrad D.. Automated training sample definition for seasonal burned area mapping[J],2020,160:107-123.
APA	Malambo, Lonesome,&Heatwole, Conrad D..(2020).Automated training sample definition for seasonal burned area mapping.ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,160,107-123.
MLA	Malambo, Lonesome,et al."Automated training sample definition for seasonal burned area mapping".ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 160(2020):107-123.