中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales

文献类型：期刊论文

作者Zhu, Wanxue2,3; Sun, Zhigang2,3,4,5; Yang, Ting4,5; Li, Jing2; Peng, Jinbang2,3; Zhu, Kangying2,3; Li, Shiji2,3; Gong, Huarui2,3; Lyu, Yun2,3; Li, Binbin2
刊名COMPUTERS AND ELECTRONICS IN AGRICULTURE
出版日期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
DOI10.1016/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.
WOS关键词AREA INDEX ; VEGETATION INDEXES ; WINTER-WHEAT ; SPECTRAL REFLECTANCE ; RADIATIVE-TRANSFER ; DIGITAL IMAGES ; CANOPY ; INVERSION ; MODEL ; BIOMASS
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研究方向Agriculture ; Computer Science
语种英语
WOS记录号WOS:000596390600004
出版者ELSEVIER SCI LTD
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)
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.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Ecosyst Network Observat & Modeling, Beijing 100101, Peoples R China
3.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Shandong Dongying Inst Geog Sci, Dongying 257000, Peoples R China
5.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, CAS Engn Lab Yellow River Delta Modern Agr, Beijing 100101, Peoples R China
6.Chinese Acad Sci, Res Ctr UAV Applicat & Regulat, Beijing 100101, Peoples R China
7.Inst UAV Applicat Res, Tianjin 301800, Tianjin, 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.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。