Optimizing Feature Selection of Individual Crop Types for Improved Crop Mapping

doi:10.3390/rs12010162

	Optimizing Feature Selection of Individual Crop Types for Improved Crop Mapping
	Yin, Leikun 1,3; You, Nanshan 2; Zhang, Geli 1; Huang, Jianxi 1; Dong, Jinwei 2
刊名	REMOTE SENSING
	2020
卷号	12 期号:1 页码:20
关键词	crop mapping feature selection spectro-temporal feature separability index Sentinel-2 Random Forest
DOI	10.3390/rs12010162
通讯作者	Zhang, Geli(geli.zhang@cau.edu.cn)
英文摘要	Accurate crop planting area information is of significance for understanding regional food security and agricultural development planning. While increasing numbers of medium resolution satellite imagery and improved classification algorithms have been used for crop mapping, limited efforts have been made in feature selection, despite its vital impacts on crop classification. Furthermore, different crop types have their unique spectral and phenology characteristics; however, the different features of individual crop types have not been well understood and considered in previous studies of crop mapping. Here, we examined an optimized strategy to integrate specific features of individual crop types for mapping an improved crop type layer in the Sanjiang Plain, a new food bowl in China, by using all Sentinel-2 time series images in 2018. First, an automatic spectro-temporal feature selection (ASTFS) method was used to obtain optimal features for individual crops (rice, corn, and soybean), including sorting all features by the global separability indices for each crop and removing redundant features by accuracy changes when adding new features. Second, the ASTFS-based optimized feature sets for individual crops were used to produce three crop probability maps with the Random Forest classifier. Third, the probability maps were then composited into the final crop layer by considering the probability of each crop at every pixel. The resultant crop layer showed an improved accuracy (overall accuracy = 93.94%, Kappa coefficient = 0.92) than the other classifications without such a feature optimizing process. Our results indicate the potential of the ASTFS method for improving regional crop mapping.
资助项目	National Natural Science Foundation of China[41871349] ; National Natural Science Foundation of China[41671418] ; National Natural Science Foundation of China[41971383] ; Key Research Program of Frontier Sciencesof the Chinese Academy of Sciences (CAS)[QYZDB-SSW-DQC005] ; Thousand Youth Talents Plan ; Strategic Priority Research Program[XDA19040301]
WOS关键词	TIME-SERIES DATA ; RANDOM FOREST ; SPECTRAL INDEXES ; AREA ESTIMATION ; MODIS ; CLASSIFICATION ; LANDSAT ; YIELD ; CORN ; AGRICULTURE
WOS研究方向	Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000515391700162
资助机构	National Natural Science Foundation of China ; Key Research Program of Frontier Sciencesof the Chinese Academy of Sciences (CAS) ; Thousand Youth Talents Plan ; Strategic Priority Research Program
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/132571]
专题	中国科学院地理科学与资源研究所
通讯作者	Zhang, Geli
作者单位	1.China Agr Univ, Coll Land Sci & Technol, Beijing 100193, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 3.Shandong Agr Univ, Sch Informat Sci & Engn, Tai An 271018, Shandong, Peoples R China
推荐引用方式 GB/T 7714	Yin, Leikun,You, Nanshan,Zhang, Geli,et al. Optimizing Feature Selection of Individual Crop Types for Improved Crop Mapping[J]. REMOTE SENSING,2020,12(1):20.
APA	Yin, Leikun,You, Nanshan,Zhang, Geli,Huang, Jianxi,&Dong, Jinwei.(2020).Optimizing Feature Selection of Individual Crop Types for Improved Crop Mapping.REMOTE SENSING,12(1),20.
MLA	Yin, Leikun,et al."Optimizing Feature Selection of Individual Crop Types for Improved Crop Mapping".REMOTE SENSING 12.1(2020):20.