An Integrated Land Cover Mapping Method Suitable for Low-Accuracy Areas in Global Land Cover Maps

被引:5
作者
Zeng, Tian [1 ]
Wang, Lei [1 ,2 ,3 ]
Zhang, Zengxiang [4 ]
Wen, Qingke [4 ]
Wang, Xiao [4 ]
Yu, Le [5 ]
机构
[1] Chinese Acad Sci, Key Lab Tibetan Environm Changes & Land Surface P, Inst Tibetan Plateau Res, Beijing 100101, Peoples R China
[2] CAS Ctr Excellence Tibetan Plateau Earth Sci, Beijing 100101, Peoples R China
[3] CAS Ctr Excellence Tibetan Plateau Earth Sci, Beijing 100101, Peoples R China
[4] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Beijing 100101, Peoples R China
[5] Tsinghua Univ, Ctr Earth Syst Sci, Minist Educ, Key Lab Earth Syst Modeling, Beijing 100084, Peoples R China
基金
中国国家自然科学基金;
关键词
land cover classification; low-accuracy area; classification algorithms; support vector machine; topographical data; classification accuracy; CLASSIFICATION; SATELLITE; VARIABILITY; ALGORITHMS; CONTINUITY; DATABASE; FUSION;
D O I
10.3390/rs11151777
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In land cover mapping, an area with complex topography or heterogeneous land covers is usually poorly classified and therefore defined as a low-accuracy area. The low-accuracy areas are important because they restrict the overall accuracy (OA) of global land cover classification (LCC) data generated. In this paper, low-accuracy areas in China (extracted from the MODIS global LCC maps) were taken as examples, identified as the regions having lower accuracy than the average OA of China. An integrated land cover mapping method targeting low-accuracy regions was developed and tested in eight representative low-accuracy regions of China. The method optimized procedures of image choosing and sample selection based on an existent visually-interpreted regional LCC dataset with high accuracies. Five algorithms and 16 groups of classification features were compared to achieve the highest OA. The support vector machine (SVM) achieved the highest mean OA (81.5%) when only spectral bands were classified. Aspect tended to attenuate OA as a classification feature. The optimal classification features for different regions largely depends on the topographic feature of vegetation. The mean OA for eight low-accuracy regions was 84.4% by the proposed method in this study, which exceeded the mean OA of most precedent global land cover datasets. The new method can be applied worldwide to improve land cover mapping of low-accuracy areas in global land cover maps.
引用
收藏
页数:20
相关论文
共 50 条
[21]   Inferring Spatial Distribution Patterns in Web Maps for Land Cover Mapping [J].
Liu, Yang ;
Lan, Zeying ;
Xing, Hanfa .
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2019, 119 (02) :311-330
[22]   Multisensor approach to land use and land cover mapping in Brazilian Amazon [J].
Prudente, Victor Hugo Rohden ;
Skakun, Sergii ;
Oldoni, Lucas Volochen ;
Xaud, Haron A. M. ;
Xaud, Maristela R. ;
Adami, Marcos ;
Sanches, Ieda Del ' Arco .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2022, 189 :95-109
[23]   Towards a common validation sample set for global land-cover mapping [J].
Zhao, Yuanyuan ;
Gong, Peng ;
Yu, Le ;
Hu, Luanyun ;
Li, Xueyan ;
Li, Congcong ;
Zhang, Haiying ;
Zheng, Yaomin ;
Wang, Jie ;
Zhao, Yongchao ;
Cheng, Qu ;
Liu, Caixia ;
Liu, Shuang ;
Wang, Xiaoyi .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2014, 35 (13) :4795-4814
[24]   Comparing global and local land cover maps for ecosystem management in the Himalayas [J].
Aryal, Kishor ;
Apan, Armando ;
Maraseni, Tek .
REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT, 2023, 30
[25]   An overview of 21 global and 43 regional land-cover mapping products [J].
Grekousis, George ;
Mountrakis, Giorgos ;
Kavouras, Marinos .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2015, 36 (21) :5309-5335
[26]   CONSENSUAL CLUSTERING FOR LAND COVER MAPPING [J].
Campedel, Marine ;
Kyrgyzov, Ivan .
2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2012, :7294-7297
[27]   Supervised methods of image segmentation accuracy assessment in land cover mapping [J].
Costa, Hugo ;
Foody, Giles M. ;
Boyd, Doreen S. .
REMOTE SENSING OF ENVIRONMENT, 2018, 205 :338-351
[28]   Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps [J].
Kim, Yeseul ;
Park, No-Wook ;
Lee, Kyung-Do .
REMOTE SENSING, 2017, 9 (09)
[29]   Land cover mapping of wetland areas in an agricultural landscape using SAR and Landsat imagery [J].
Castaneda, C. ;
Ducrot, D. .
JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2009, 90 (07) :2270-2277
[30]   A simple, fast, and accurate method for land cover mapping in Mongolia [J].
Phan, Thanh-Noi ;
Dashpurev, Batnyambuu ;
Wiemer, Felix ;
Lehnert, Lukas W. .
GEOCARTO INTERNATIONAL, 2022, 37 (26) :14432-14450