Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales

doi:10.1016/j.compag.2020.105786

	Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales
	Zhu, Wanxue 2,7; Sun, Zhigang 2,3,4,7; Yang, Ting 3,4; Li, Jing 7; Peng, Jinbang 2,7; Zhu, Kangying 2,7; Li, Shiji 2,7; Gong, Huarui 2,7; Lyu, Yun 2,7; Li, Binbin 7
刊名	COMPUTERS AND ELECTRONICS IN AGRICULTURE
	2020-11-01
卷号	178 页码:16
关键词	Unmanned aerial vehicle (UAV) Hyperspectral Chlorophyll Machine learning Precision agriculture
ISSN号	0168-1699
DOI	10.1016/j.compag.2020.105786
通讯作者	Sun, Zhigang(sun.zhigang@igsnrr.ac.cn)
英文摘要	Leaf chlorophyll content (LCC) is a crucial indicator of nutrition in crop plants and can be applied to assess the adequacy of nitrogen (N) fertilizer for crops while reducing N losses to farmland. This study estimated the LCC of maize and wheat, and comprehensively examined the effects of the spectral information and spatial scale of unmanned aerial vehicle (UAV) imagery, and the effects of phenotype and phenology on LCC estimation. A Cubert S185 hyperspectral camera onboard a DJI M600 Pro was used to conduct six flight missions over a longterm experimental field with five N applications (0, 70, 140, 210, and 280 kg N ha-1) and two irrigation levels (60% and 80% field water capacity) during the growing seasons of wheat and maize in 2019. Four regression algorithms, that is, multi-variable linear regression, random forest, backpropagation neural network, and support vector machine, were used for modeling. Leaf, canopy, and hybrid scale hyperspectral variables (H -variables) were used as inputs for the statistical LCC models. Optimal H-variables for modeling were determined by Pearson correlation filtering followed by a recursive feature elimination procedure. The results showed that (1) H-variables at the canopyand leaf-scales were appropriate for wheat and maize LCC estimation, respectively; (2) the robustness of LCC estimation was in the order of the flowering stage > heading stage > grain filling stage for wheat and early grain filling stage > flowering stage > jointing stage for maize; (3) the reflectance of the red edge, green, and blue bands were the most important inputs for LCC modeling, and the optimal vegetation indices differed for the various growth stages and crops; and (4) all four algorithms maintained an acceptable accuracy with respect to LCC estimation, although random forest and support vector machine were slightly better. This study is valuable for the design of appropriate schemes for the spectral and scale issues of UAV sensors for LCC estimation regarding specific crop phenotype and phenology periods, and further boosts the applications of UAVs in precision agriculture.
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDA23050102] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19040303] ; Key Projects of the Chinese Academy of Sciences[KJZD-EW-G20] ; National Key Research and Development Program of China[2017YFC0503805] ; National Natural Science Foundation of China[31870421] ; Tianjin Intelligent Manufacturing Project (Tianjin-IMP-2)
WOS关键词	AREA INDEX ; VEGETATION INDEXES ; WINTER-WHEAT ; SPECTRAL REFLECTANCE ; RADIATIVE-TRANSFER ; DIGITAL IMAGES ; CANOPY ; INVERSION ; MODEL ; BIOMASS
WOS研究方向	Agriculture ; Computer Science
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000596390600004
资助机构	Strategic Priority Research Program of the Chinese Academy of Sciences ; Key Projects of the Chinese Academy of Sciences ; National Key Research and Development Program of China ; National Natural Science Foundation of China ; Tianjin Intelligent Manufacturing Project (Tianjin-IMP-2)
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/137298]
专题	中国科学院地理科学与资源研究所
通讯作者	Sun, Zhigang
作者单位	1.Inst UAV Applicat Res, Tianjin 301800, Tianjin, Peoples R China 2.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Shandong Dongying Inst Geog Sci, Dongying 257000, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, CAS Engn Lab Yellow River Delta Modern Agr, Beijing 100101, Peoples R China 5.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 6.Chinese Acad Sci, Res Ctr UAV Applicat & Regulat, Beijing 100101, Peoples R China 7.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Ecosyst Network Observat & Modeling, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Wanxue,Sun, Zhigang,Yang, Ting,et al. Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2020,178:16.
APA	Zhu, Wanxue.,Sun, Zhigang.,Yang, Ting.,Li, Jing.,Peng, Jinbang.,...&Liao, Xiaohan.(2020).Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales.COMPUTERS AND ELECTRONICS IN AGRICULTURE,178,16.
MLA	Zhu, Wanxue,et al."Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales".COMPUTERS AND ELECTRONICS IN AGRICULTURE 178(2020):16.