Analyzing the Sensitivity of Crops Classification Accuracy Based on MODIS EVI Time Series and History Ground Reference Data

	Analyzing the Sensitivity of Crops Classification Accuracy Based on MODIS EVI Time Series and History Ground Reference Data
	Muhammad, Shakir 1; Zhan, Yulin 1; Niu, Zheng 1; Wang, Li 1; Hao, Pengyu 1
刊名	CANADIAN JOURNAL OF REMOTE SENSING
	2015
卷号	41 期号:6 页码:4922-4934
通讯作者	Zhan, YL (reprint author), Chinese Acad Sci, Inst Remote Sensing & Digital Earth, State Key Lab Remote Sensing Sci, POB 9718,20 Datun Rd, Beijing 100094, Peoples R China.
英文摘要	An improved spectral profile-based classification method was developed to discriminate corn, alfalfa, and winter wheat in the U.S. state of Kansas. Unlike other classification procedures, this method uses historical field reference data as training samples. An artificial immune network (AIN) algorithm, namely the artificial antibody network (ABNet), was tested as a classifier, combining historical field reference data and moderate-resolution imaging spectroradiometer (MODIS)-enhanced vegetation index (EVI) images. Historical field reference data from the years 2009 to 2012 were used to classify the three crops for 2013 data. A new method was developed to select the purest pixels from cropland data layer (CDL). Historical reference data were used in two different methods to classify crops in 2013: (i) single-year historical data and (ii) multiyear data used in four different combinations. Using method (i), classification was most accurate when the most recent year of training data was utilized. The accuracy of method (ii) increased with the number of years of data used for training the classifier. Results ranged from 81% to 92% overall accuracies, with the exception of the year 2012, where a severe drought created anomalous spectral profiles for all crops in the study area. ResumeUne methode amelioree de classification spectrale basee sur les profils a ete developpee pour discriminer le mais, la luzerne et le ble d'hiver dans l'Etat americain du Kansas. Contrairement a d'autres procedures de classification, cette methode utilise les donnees historiques de reference terrain comme echantillons d'entrainement de la methode. Un algorithme de reseau immunitaire artificiel (AIN), a savoir le Artificial Antibody Network (ABNet), a ete teste comme classificateur, combinant les donnees historiques de reference terrain et les images MODIS EVI. Les donnees historiques de reference terrain des annees 2009 a 2012 ont ete utilisees pour classifier les trois cultures des donnees de 2013. Une nouvelle methode a ete developpee pour selectionner les pixels les plus purs de la couche de donnees des terres cultivees (CDL). Les donnees historiques de reference ont ete utilisees dans deux methodes differentes pour classifier les cultures en 2013: (a) une seule annee de donnees historiques et (b) des donnees pluriannuelles utilisees dans quatre combinaisons differentes. L'utilisation de la methode de classification (a) etait la plus precise lorsque l'annee la plus recente des donnees d'entrainement etait utilisee. La precision de la methode (b) augmentait avec le nombre d'annees de donnees utilise pour l'entrainement du classificateur. Les resultats variaient de 81% a 92% pour les precisions globales, a l'exception de l'annee 2012, oU une grave secheresse a cree des profils spectraux anormaux pour toutes les cultures dans la zone d'etude.
研究领域[WOS]	Remote Sensing
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:000370398000004
内容类型	期刊论文
源URL	[http://ir.ceode.ac.cn/handle/183411/38062]
专题	遥感与数字地球研究所_SCI/EI期刊论文_期刊论文
作者单位	1.[Muhammad, Shakir 2.Zhan, Yulin 3.Wang, Li] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, State Key Lab Remote Sensing Sci, POB 9718,20 Datun Rd, Beijing 100094, Peoples R China 4.[Muhammad, Shakir 5.Niu, Zheng 6.Wang, Li 7.Hao, Pengyu] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Muhammad, Shakir,Zhan, Yulin,Niu, Zheng,et al. Analyzing the Sensitivity of Crops Classification Accuracy Based on MODIS EVI Time Series and History Ground Reference Data[J]. CANADIAN JOURNAL OF REMOTE SENSING,2015,41(6):4922-4934.
APA	Muhammad, Shakir,Zhan, Yulin,Niu, Zheng,Wang, Li,&Hao, Pengyu.(2015).Analyzing the Sensitivity of Crops Classification Accuracy Based on MODIS EVI Time Series and History Ground Reference Data.CANADIAN JOURNAL OF REMOTE SENSING,41(6),4922-4934.
MLA	Muhammad, Shakir,et al."Analyzing the Sensitivity of Crops Classification Accuracy Based on MODIS EVI Time Series and History Ground Reference Data".CANADIAN JOURNAL OF REMOTE SENSING 41.6(2015):4922-4934.