Land Cover Mapping in Cloud-Prone Tropical Areas Using Sentinel-2 Data: Integrating Spectral Features with Ndvi Temporal Dynamics

doi:10.3390/rs12071163

	Land Cover Mapping in Cloud-Prone Tropical Areas Using Sentinel-2 Data: Integrating Spectral Features with Ndvi Temporal Dynamics
	Huang, Chong 1,2; Zhang, Chenchen 2,3; He, Yun 2,3; Liu, Qingsheng 2; Li, He 2; Su, Fenzhen 2; Liu, Gaohuan 2; Bridhikitti, Arika 4
刊名	REMOTE SENSING
	2020-04-01
卷号	12 期号:7 页码:18
关键词	land cover mapping cloud-prone areas Sentinel-2 time series NDVI statistical indices
DOI	10.3390/rs12071163
通讯作者	Li, He(lih@lreis.ac.cn)
英文摘要	Accurate remote sensing and mapping of land cover in the tropics remain difficult tasks since data gaps and a heterogenic landscape make it challenging to perform land cover classification. In this paper, we proposed a multi-feature classification method to integrate temporal statistical features with spectral and textural features. This method is designed to improve the accuracy of land cover classification in cloud-prone tropical regions. Sentinel-2 images were used to construct an NDVI stack for a time-series statistical analysis to characterize the temporal variance of land cover. Two statistical indices were calculated and used to represent the variation in annual vegetation. These indices included the mean (NDVI_mean) and coefficient of variation (NDVI_cv) for the NDVI time series. The temporal statistical features were then integrated with spectral and textural features extracted from high-quality Sentinel-2 imagery for Random Forest classification. The performance and contribution of different combinations were assessed based on their classification accuracies. Our results show that the time-series statistical analysis is an effective way to represent land cover category information contained in annual NDVI variance. The method uses clear pixels from dense low-quality images to obtain the NDVI statistical characteristics, thus, to reduce the influence of random factors such as weather conditions on single-date image. The addition of NDVI_mean and NDVI_cv can improve the separability among most types of land cover. The overall accuracy and the kappa coefficient reached values of 0.8913 and 0.8514 when NDVI_mean and NDVI_cv were integrated. Furthermore, the time-series statistical analysis has less stringent requirements regarding image quality and features a high computational efficiency, which shows its great potential to improve the overall accuracy of land cover classification at regional scales in cloud-prone tropical regions.
资助项目	CAS Earth Big Data Science Project[XDA19060302] ; National Science Foundation of China[41561144012] ; National Science Foundation of China[41661144030] ; Innovation Project of LREIS[O88RA303YA]
WOS关键词	RESOLUTION SATELLITE DATA ; TIME-SERIES ; RANDOM FOREST ; CLASSIFICATION ; ACCURACY ; CROP ; SEGMENTATION ; AGREEMENT ; IMAGERY ; SENSOR
WOS研究方向	Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000537709600113
资助机构	CAS Earth Big Data Science Project ; National Science Foundation of China ; Innovation Project of LREIS
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/159476]
专题	中国科学院地理科学与资源研究所
通讯作者	Li, He
作者单位	1.Chinese Acad Sci, CAS Engn Lab Yellow River Delta Modern Agr, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Mahidol Univ, Sch Multidisciplinary, Environm Engn & Disaster Management Program, Kanchanaburi Campus, Sai Yok 71150, Kanchanaburi, Thailand
推荐引用方式 GB/T 7714	Huang, Chong,Zhang, Chenchen,He, Yun,et al. Land Cover Mapping in Cloud-Prone Tropical Areas Using Sentinel-2 Data: Integrating Spectral Features with Ndvi Temporal Dynamics[J]. REMOTE SENSING,2020,12(7):18.
APA	Huang, Chong.,Zhang, Chenchen.,He, Yun.,Liu, Qingsheng.,Li, He.,...&Bridhikitti, Arika.(2020).Land Cover Mapping in Cloud-Prone Tropical Areas Using Sentinel-2 Data: Integrating Spectral Features with Ndvi Temporal Dynamics.REMOTE SENSING,12(7),18.
MLA	Huang, Chong,et al."Land Cover Mapping in Cloud-Prone Tropical Areas Using Sentinel-2 Data: Integrating Spectral Features with Ndvi Temporal Dynamics".REMOTE SENSING 12.7(2020):18.