Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China

doi:10.3390/f10111040

	Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China
	Cheng, Kai 1,2; Wang, Juanle 2,3
刊名	FORESTS
	2019-11-01
卷号	10 期号:11 页码:18
关键词	forest type time-weighted dynamic time warping random forest support vector machine mountain area southern China
DOI	10.3390/f10111040
通讯作者	Wang, Juanle(wangjl@igsnrr.ac.cn)
英文摘要	Efficient methodologies for mapping forest types in complicated mountain areas are essential for the implementation of sustainable forest management practices and monitoring. Existing solutions dedicated to forest-type mapping are primarily focused on supervised machine learning algorithms (MLAs) using remote sensing time-series images. However, MLAs are challenged by complex and problematic forest type compositions, lack of training data, loss of temporal data caused by clouds obscuration, and selection of input feature sets for mountainous areas. The time-weighted dynamic time warping (TWDTW) is a supervised classifier, an adaptation of the dynamic time warping method for time series analysis for land cover classification. This study evaluates the performance of the TWDTW method that uses a combination of Sentinel-2 and Landsat-8 time-series images when applied to complicated mountain forest-type classifications in southern China with complex topographic conditions and forest-type compositions. The classification outputs were compared to those produced by MLAs, including random forest (RF) and support vector machine (SVM). The results presented that the three forest-type maps obtained by TWDTW, RF, and SVM have high consistency in spatial distribution. TWDTW outperformed SVM and RF with mean overall accuracy and mean kappa coefficient of 93.81% and 0.93, respectively, followed by RF and SVM. Compared with MLAs, TWDTW method achieved the higher classification accuracy than RF and SVM, with even less training data. This proved the robustness and less sensitivities to training samples of the TWDTW method when applied to mountain forest-type classifications.
资助项目	Strategic Priority Research Program (class A) of the Chinese Academy of Sciences[XDA19040501] ; The 13th Five-year Informatization Plan of the Chinese Academy of Sciences[XXH13505-07] ; Construction Project of China Knowledge Center for Engineering Sciences and Technology[CKCEST-2019-3-6]
WOS关键词	LAND-COVER ; IMAGE CLASSIFICATION ; CROP CLASSIFICATION ; SERIES ANALYSIS ; MODIS ; SELECTION ; TERRAIN ; SCALE ; INDEX ; US
WOS研究方向	Forestry
语种	英语
出版者	MDPI
WOS记录号	WOS:000502262700106
资助机构	Strategic Priority Research Program (class A) of the Chinese Academy of Sciences ; The 13th Five-year Informatization Plan of the Chinese Academy of Sciences ; Construction Project of China Knowledge Center for Engineering Sciences and Technology
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/130727]
专题	中国科学院地理科学与资源研究所
通讯作者	Wang, Juanle
作者单位	1.Univ Chinese Acad Sci, Beijing 10010, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 10010, Peoples R China 3.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Kai,Wang, Juanle. Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China[J]. FORESTS,2019,10(11):18.
APA	Cheng, Kai,&Wang, Juanle.(2019).Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China.FORESTS,10(11),18.
MLA	Cheng, Kai,et al."Forest-Type Classification Using Time-Weighted Dynamic Time Warping Analysis in Mountain Areas: A Case Study in Southern China".FORESTS 10.11(2019):18.