An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping

doi:10.3390/ijgi7020075

	An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping
	Guan, Xudong 1,2; Liu, Gaohuan 1; Huang, Chong 1; Meng, Xuelian 3; Liu, Qingsheng 1; Wu, Chunsheng 1; Ablat, Xarapat 1,2; Chen, Zhuoran 1,2; Wang, Qiang 1,2
刊名	ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
	2018-02-01
卷号	7 期号:2 页码:22
关键词	dynamic time warping (DTW) remote sensing Lower Mekong Basin MODIS time series crops cropland classification
ISSN号	2220-9964
DOI	10.3390/ijgi7020075
通讯作者	Liu, Gaohuan(liugh@lreis.ac.cn)
英文摘要	This paper proposes an open-boundary locally weighted dynamic time warping (OLWDTW) method using MODIS Normalized Difference Vegetation Index (NDVI) time-series data for cropland recognition. The method solves the problem of flexible planting times for crops in Southeast Asia, which has sufficient thermal and water conditions. For NDVI time series starting at the beginning of the year and terminating at the end of the year, the method can separate the non-growing season cycle and growing season cycle for crops. The non-growing season cycle may provide some useful information for crop recognition, such as soil conditions. However, the shape of the growing season's NDVI time series for crops is the key to separating cropland from other land cover types because the shape contains all of the crop growth information. The principle of the OLWDTW method is to enhance the effects of the growing season cycle on the NDVI time series by adding a local weight to the growing season when comparing the similarity of time series based on the open-boundary dynamic time warping (DTW) method. Experiments with two satellite datasets located near the Khorat Plateau in the Lower Mekong Basin validate that OLWDTW effectively improves the precision of cropland recognition compared to a non-weighted open-boundary DTW method in terms of overall accuracy. The method's classification accuracy on cropland exceeds the non-weighted open-boundary DTW by 5-7%. In future studies, an open-boundary self-adaption locally weighted DTW and a more effective combination rule for different crop types should be explored for the method's best performance and highest extraction accuracy for cropland.
资助项目	Innovation Project of LREIS[O88RA303YA] ; National Science-Technology Support Plan Projects[2013BAD05B03] ; National Natural Science Foundation of China[41561144012] ; National Natural Science Foundation of China[41501430] ; National Natural Science Foundation of China[41671422] ; National Natural Science Foundation of China[41661144030] ; National Natural Science Foundation of China[41471335]
WOS关键词	MULTITEMPORAL MODIS IMAGES ; TERM VEGETATION TRENDS ; PADDY RICE AGRICULTURE ; SERIES ANALYSIS ; MEKONG DELTA ; CLASSIFICATION ; YIELDS ; EXTENT ; AREAS ; GIMMS
WOS研究方向	Physical Geography ; Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000427524600038
资助机构	Innovation Project of LREIS ; National Science-Technology Support Plan Projects ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/57218]
专题	中国科学院地理科学与资源研究所
通讯作者	Liu, Gaohuan
作者单位	1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Louisiana State Univ, Dept Geog & Anthropol, Baton Rouge, LA 70803 USA
推荐引用方式 GB/T 7714	Guan, Xudong,Liu, Gaohuan,Huang, Chong,et al. An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping[J]. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,2018,7(2):22.
APA	Guan, Xudong.,Liu, Gaohuan.,Huang, Chong.,Meng, Xuelian.,Liu, Qingsheng.,...&Wang, Qiang.(2018).An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping.ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,7(2),22.
MLA	Guan, Xudong,et al."An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping".ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION 7.2(2018):22.