干旱区生态环境知识资源中心(Arid): Direct, ECOC, ND and END Frameworks-Which One Is the Best? An Empirical Study of Sentinel-2A MSIL1C Image Classification for Arid-Land Vegetation Mapping in the Ili River Delta, Kazakhstan

Arid

DOI	10.3390/rs11161953
	Direct, ECOC, ND and END Frameworks-Which One Is the Best? An Empirical Study of Sentinel-2A MSIL1C Image Classification for Arid-Land Vegetation Mapping in the Ili River Delta, Kazakhstan
	Samat, Alim 1,2,3; Yokoya, Naoto 4; Du, Peijun 5; Liu, Sicong 6; Ma, Long 1,2,3; Ge, Yongxiao 1,2; Issanova, Gulnura 7,8; Saparov, Abdula 9; Abuduwaili, Jilili 1,2,3; Lin, Cong 5
通讯作者	Samat, Alim
来源期刊	REMOTE SENSING
EISSN	2072-4292
出版年	2019
卷号	11 期号:16
英文摘要	To facilitate the advances in Sentinel-2A products for land cover from Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat imagery, Sentinel-2A MultiSpectral Instrument Level-1C (MSIL1C) images are investigated for large-scale vegetation mapping in an arid land environment that is located in the Ili River delta, Kazakhstan. For accurate classification purposes, multi-resolution segmentation (MRS) based extended object-guided morphological profiles (EOMPs) are proposed and then compared with conventional morphological profiles (MPs), MPs with partial reconstruction (MPPR), object-guided MPs (OMPs), OMPs with mean values (OMPsM), and object-oriented (OO)-based image classification techniques. Popular classifiers, such as C4.5, an extremely randomized decision tree (ERDT), random forest (RaF), rotation forest (RoF), classification via random forest regression (CVRFR), ExtraTrees, and radial basis function (RBF) kernel-based support vector machines (SVMs) are adopted to answer the question of whether nested dichotomies (ND) and ensembles of ND (END) are truly superior to direct and error-correcting output code (ECOC) multiclass classification frameworks. Finally, based on the results, the following conclusions are drawn: 1) the superior performance of OO-based techniques over MPs, MPPR, OMPs, and OMPsM is clear for Sentinel-2A MSIL1C image classification, while the best results are achieved by the proposed EOMPs; 2) the superior performance of ND, ND with class balancing (NDCB), ND with data balancing (NDDB), ND with random-pair selection (NDRPS), and ND with further centroid (NDFC) over direct and ECOC frameworks is not confirmed, especially in the cases of using weak classifiers for low-dimensional datasets; 3) from computationally efficient, high accuracy, redundant to data dimensionality and easy of implementations points of view, END, ENDCB, ENDDB, and ENDRPS are alternative choices to direct and ECOC frameworks; 4) surprisingly, because in the ensemble learning (EL) theorem, weaker classifiers (ERDT here) always have a better chance of reaching the trade-off between diversity and accuracy than stronger classifies (RaF, ExtraTrees, and SVM here), END with ERDT (END-ERDT) achieves the best performance with less than a 0.5% difference in the overall accuracy (OA) values, but is 100 to 10000 times faster than END with RaF and ExtraTrees, and ECOC with SVM while using different datasets with various dimensions; and, 5) Sentinel-2A MSIL1C is better choice than the land cover products from MODIS and Landsat imagery for vegetation species mapping in an arid land environment, where the vegetation species are critically important, but sparsely distributed.
英文关键词	ND END ECOC MRS Extended object-guided morphological profiles Multiclass classification Arid-land vegetation mapping Sentinel-2A MSIL1C Central Asia
类型	Article
语种	英语
国家	Peoples R China ; Japan ; Kazakhstan
开放获取类型	gold, Green Submitted
收录类别	SCI-E
WOS记录号	WOS:000484387600116
WOS关键词	SUPPORT-VECTOR-MACHINE ; SPECTRAL-SPATIAL CLASSIFICATION ; EXTREME LEARNING MACHINES ; ARTIFICIAL NEURAL-NETWORK ; RANDOM FOREST ; COVER CLASSIFICATION ; HYPERSPECTRAL DATA ; CENTRAL-ASIA ; TIME-SERIES ; SPECIES RICHNESS
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
来源机构	中国科学院新疆生态与地理研究所 ; 南京大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/218406
作者单位	1.Chinese Acad Sci, Xinjiang Inst Ecol & Geog, State Key Lab Desert & Oasis Ecol, Urumqi 830011, Peoples R China; 2.Chinese Acad Sci, Res Ctr Ecol & Environm Cent Asia, Urumqi 830011, Peoples R China; 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China; 4.RIKEN Ctr Adv Intelligence Project, Tokyo 1030027, Japan; 5.Nanjing Univ, Dept Geog Informat Sci, Nanjing 210093, Jiangsu, Peoples R China; 6.Tongji Univ, Coll Surveying & Geoinformat, Shanghai 200092, Peoples R China; 7.Al Farabi Kazakh Natl Univ, Fac Geog & Environm Sci, Alma Ata 050040, Kazakhstan; 8.CAS, Res Ctr Ecol & Environm Cent Asia Almaty, Alma Ata 050060, Kazakhstan; 9.UU Uspanov Kazakh Res Inst Soil Sci & Agrochem, Alma Ata 050060, Kazakhstan
推荐引用方式 GB/T 7714	Samat, Alim,Yokoya, Naoto,Du, Peijun,et al. Direct, ECOC, ND and END Frameworks-Which One Is the Best? An Empirical Study of Sentinel-2A MSIL1C Image Classification for Arid-Land Vegetation Mapping in the Ili River Delta, Kazakhstan[J]. 中国科学院新疆生态与地理研究所, 南京大学,2019,11(16).
APA	Samat, Alim.,Yokoya, Naoto.,Du, Peijun.,Liu, Sicong.,Ma, Long.,...&Lin, Cong.(2019).Direct, ECOC, ND and END Frameworks-Which One Is the Best? An Empirical Study of Sentinel-2A MSIL1C Image Classification for Arid-Land Vegetation Mapping in the Ili River Delta, Kazakhstan.REMOTE SENSING,11(16).
MLA	Samat, Alim,et al."Direct, ECOC, ND and END Frameworks-Which One Is the Best? An Empirical Study of Sentinel-2A MSIL1C Image Classification for Arid-Land Vegetation Mapping in the Ili River Delta, Kazakhstan".REMOTE SENSING 11.16(2019).