Global Land Cover Mapping Using Annual Clear-sky Composites from FY3D/MERSI-II

被引:3
作者
Wang, Yuanyuan [1 ,2 ]
Li, Guicai [1 ,2 ]
机构
[1] China Meteorol Adm, Key Lab Radiometr Calibrat & Validat Environm Sat, Natl Satellite Meteorol Ctr, Beijing, Peoples R China
[2] FengYun Meteorol Satellite Innovat Ctr FY MSIC, Beijing, Peoples R China
关键词
SPATIAL-RESOLUTION; DATA SET; MODIS; AVHRR; VEGETATION; CLASSIFICATION; PERFORMANCE; ALGORITHMS; SATELLITE; MAPS;
D O I
10.1080/01431161.2021.2019848
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Medium Resolution Spectral Imager-II (MERSI-II) on board FY-3D satellite is a visible and infrared spectral imaging instrument featured with six 250-m spatial resolution channels (blue, green, red, NIR, 10.8 mu m, 12.0 mu m). Such unique spectral and spatial attributes provide significant opportunities and challenges for land cover (LC) mapping research. This paper reports the production of a 250-m spatial resolution global LC classification (under IGBP scheme) from MERSI-II NDVI operational products from May 2019 to April 2020. To extract robust features for discriminating LC types, we adopted three classic compositing criteria (MaxNDVI, Mean8NDVI, and Mean4BT) and two new compositing criteria (3minRedBlue and 3minRedNIR) to obtain high-quality annual composites. Random Forest (RF) algorithm was used for supervised learning, and 10-fold cross validation (CV) based on 'site-splits' was implemented to evaluate classification accuracy. The derived MERIS-II LC map was compared at pixel level with two widely used LC products (MODIS and VIIRS), and consistency among the three maps was investigated. Results showed that the higher resolution afforded by 250-m MERSI-II data in combination with a refined input features produced a global LC map with an overall accuracy of 79-86%. Most classes exhibited low commission and omission errors except for some classes of mixed nature (i.e. wetland, cropland/natural vegetation mosaic, savanna, woody savanna). The MERSI-II LC map generally agreed better with MODIS than with VIIRS, and the proportion of land pixels (excluding Antarctic) for which MERSI-II shows the same LC label with either MODIS or VIIRS is very large (0.70-0.82). Composite data contributed differently to total accuracy, with Mean8NDVI being the most spatial coherent and most contributive and MaxNDVI being the opposite. The other three composites (Mean4BT, 3minRedBlue, and 3minRedNIR) showed moderate spatial coherence and contributed to classification variedly by extracting information from different phenology phases. The unique 250-m blue and green bands of MERSI-II were found to be helpful to discriminate between wetland and needleleaf forest in high latitudes and between cities and grassland. This study confirms that with the RF algorithm (one of the state-of-art supervised machine learning algorithms) and image compositing techniques, accurate LC map can be derived from MERSI-II. Future work will attempt to include more bands and compositing criteria to further improve classification accuracy.
引用
收藏
页码:510 / 531
页数:22
相关论文
共 58 条
[1]  
[Anonymous], 2021, IEEE Trans. Broadcast.
[2]   A self-adaptive approach for producing clear-sky composites from VIIRS surface reflectance datasets [J].
Bian, Jinhu ;
Li, Ainong ;
Huang, Chengquan ;
Zhang, Rui ;
Zhan, Xiwu .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 144 :189-201
[3]   Land cover characterization of Temperate East Asia using multi-temporal VEGETATION sensor data [J].
Boles, SH ;
Xiao, XM ;
Liu, JY ;
Zhang, QY ;
Munkhtuya, S ;
Chen, SQ ;
Ojima, D .
REMOTE SENSING OF ENVIRONMENT, 2004, 90 (04) :477-489
[4]   Multi-temporal compositing approaches for SPOT-4 VEGETATION [J].
Cabral, A ;
De Vasconcelos, MJP ;
Pereira, JMC ;
Bartholomé, É ;
Mayaux, P .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2003, 24 (16) :3343-3350
[5]   Assessment of multitemporal compositing techniques of MODIS and AVHRR images for burned land mapping [J].
Chuvieco, E ;
Ventura, G ;
Martín, MP ;
Gómez, I .
REMOTE SENSING OF ENVIRONMENT, 2005, 94 (04) :450-462
[6]   EVALUATION OF COMPOSITING ALGORITHMS FOR AVHRR DATA OVER LAND [J].
CIHLAR, J ;
MANAK, D ;
DIORIO, M .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1994, 32 (02) :427-437
[7]   Land change for all municipalities in Latin America and the Caribbean assessed from 250-m MODIS imagery (2001-2010) [J].
Clark, Matthew L. ;
Aide, T. Mitchell ;
Riner, George .
REMOTE SENSING OF ENVIRONMENT, 2012, 126 :84-103
[8]   Land cover classification with coarse spatial resolution data to derive continuous and discrete maps for complex regions [J].
Colditz, R. R. ;
Schmidt, M. ;
Conrad, C. ;
Hansen, M. C. ;
Dech, S. .
REMOTE SENSING OF ENVIRONMENT, 2011, 115 (12) :3264-3275
[9]   Generation and analysis of the 2005 land cover map for Mexico using 250 m MODIS data [J].
Colditz, Rene R. ;
Lopez Saldana, Gerardo ;
Maeda, Pedro ;
Argumedo Espinoza, Jesus ;
Meneses Tovar, Carmen ;
Victoria Hernandez, Arturo ;
Zermeno Benitez, Carlos ;
Cruz Lopez, Isabel ;
Ressl, Rainer .
REMOTE SENSING OF ENVIRONMENT, 2012, 123 :541-552
[10]   Global land cover classifications at 8 km spatial resolution: the use of training data derived from Landsat imagery in decision tree classifiers [J].
De Fries, RS ;
Hansen, M ;
Townshend, JRG ;
Sohlberg, R .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1998, 19 (16) :3141-3168