Welcome to Acta Agronomica Sinica，

Acta Agronomica Sinica ›› 2026, Vol. 52 ›› Issue (6): 1788-1801.doi: 10.3724/SP.J.1006.2026.53085

• TILLAGE & CULTIVATION · PHYSIOLOGY & BIOCHEMISTRY • Previous Articles     Next Articles

Estimation of leaf nitrogen content in dryland forage maize using UAV-based hyperspectral imaging and machine learning

Liang Jin-Yu**(), Yin Jia-De**(), Wang Hong-Li, Zhang Guo-Ping, Hou Hui-Zhi, Dong Bo, Ma Ming-Sheng*()   

  1. Institute of Dry Land Farming, Gansu Academy of Agricultural Sciences / Key Laboratory of High Water Utilization on Dryland of Gansu Province / Northwest Dryland Agriculture Green Low Carbon Key Laboratory, Ministry of Agriculture and Rural Affairs, Lanzhou 730070, Gansu, China
  • Received:2025-10-29 Accepted:2026-02-27 Online:2026-06-12 Published:2026-03-10
  • Contact: * Ma Ming-Sheng, E-mail: mamingsh@163.com
  • About author:

    **Contributed equally to this work

  • Supported by:
    Gansu Provincial Science and Technology Program Projects(23JRRA1340);Gansu Provincial Science and Technology Program Projects(23JRRA1335);Gansu Provincial Science and Technology Program Projects(24JRRA731);Basic Research Program Project of Gansu Academy of Agricultural Sciences(2026GAAS22-7);National Natural Science Foundation of China(32360532);Longyuan Young Talents Program

RichHTML450

12

PDF

152

Abstract:

This study integrates UAV-based hyperspectral imaging with ensemble learning to identify an optimal spectral estimation model for predicting leaf nitrogen content (LNC) in dryland forage maize, providing a methodological reference for improving production efficiency and quality. The study was conducted on the Loess Plateau in central Gansu province, China, with forage maize as the target crop. Hyperspectral data were acquired using a V185G integrated gimbal hyperspectral imaging system mounted on a UAV. Spectral indices were generated from all possible two-band combinations using original reflectance spectra, first-derivative spectra, and continuum-removed spectra. Six machine-learning algorithms were evaluated, and Voting and Stacking ensemble models were further developed to select the best-performing approach. Transformed spectra substantially strengthened the relationships between spectral indices and LNC compared with the original bands. Among the six individual models, random forest regression (RFR), K-nearest neighbors (KNN), XGBoost, and gradient boosting decision tree (GBDT) achieved relatively high accuracy across maize growth stages, with test-set R2 values of 0.7165-0.7713 and RMSE values of 2.4265-2.8296. These four models were then combined to build the ensemble models, both of which achieved test-set R2 > 0.7459 and RMSE < 2.6358. The Voting ensemble based on first-derivative spectra delivered the best performance (R2 = 0.8152, RMSE = 2.1253), indicating improved predictive accuracy and robustness through model integration. Overall, the Voting-first-derivative spectra (Voting-FDS) model enables rapid estimation of LNC at key growth stages, supporting in-season nutrient management and high-quality production in dryland forage maize.

Key words: dryland forage maize, leaf nitrogen content, hyperspectral, band selection, machine learning

Table 1

Description of the experimental treatments"

处理
Treatment		 种植密度
Planting density (×104 plant hm-2)		 施肥方式
Fertilization method
CK1 6.0 全部基施 All applied as basal fertilizer
T1 6.0 40%追施 40% applied as topdressing
T2 6.0 60%追施 60% applied as topdressing
CK2 7.5 全部基施 All applied as basal fertilizer
T3 7.5 40%追施 40% applied as topdressing
T4 7.5 60%追施 60% applied as topdressing

Table 2

Camera parameters for flight route planning"

指标
Specification		 参数
Parameter
分辨率Resolution 1000×1000 pix
探测器尺寸Detector size 6.45×6.45 mm
焦距Focal length 16 mm
最小拍照间隔Minimum capture interval 1 s

Fig. 1

Location of the study area and sampling sites This map is based on the standard map downloaded from the Standard Map Service website of the Ministry of Natural Resources, with the review approval number GS (2019) 3333. The boundaries of the base map remain unaltered. Treatments are the same as those given in Table 1."

Fig. 2

Workflow for hyperspectral image mosaicking Cuvis Export 3.2 was used to export hyperspectral images; Agisoft Metashape was used for image mosaicking; ENVI 5.6 was used to convert TIFF files to BIL format. TIFF, tagged image file format; BIL, band interleaved by line."

Fig. 3

Workflow of the ensemble machine-learning approach RFR, random forest regression; KNN, K-nearest neighbors regression; XGBoost, extreme gradient boosting; GBDT, gradient boosting decision tree; RR, ridge regression; PLSR, partial least squares regression; Voting, voting ensemble; Stacking, stacking ensemble."

Fig. 4

Original spectral features"

Fig. 5

Contour maps of correlations between narrowband spectral indices and leaf nitrogen content in forage maize OS, original spectra; FDS, first-derivative spectra; CRS, continuum-removed spectra; NDSI, normalized difference spectral index; RSI, ratio spectral index; DSI, difference spectral index."

Table 3

Optimal band combinations for narrowband spectral indices"

变换光谱
Transform spectrum		 光谱指数
Spectral indices		 相关系数
Correlation coefficient
原始光谱
Original spectrum (OS)		 NDSI (R630, R506) 0.7796**
RSI (R746, R750) 0.7137**
DSI (R630, R506) 0.7806**
一阶导数光谱
First derivative spectrum (FDS)		 NDSI (R710, R742) 0.7904**
RSI (R706, R750) 0.7851**
DSI (R710, R738) 0.7995**
连续统去除光谱
Continuum removal spectrum (CRS)		 NDSI (R570, R498) 0.8074**
RSI (R738, R454) 0.7879**
DSI (R566, R490) 0.8094**

Table 4

Accuracy comparison of six machine learning models"

模型
Model		 变换光谱
Transform spectrum		 训练集R2
Train R2		 测试集R2
Test R2		 训练集RMSE
Train RMSE		 测试集RMSE
Test RMSE
RFR 原始光谱Original spectrum (OS) 0.7370 0.7432 2.4977 2.5975
一阶导数光谱First derivative spectrum (FDS) 0.7503 0.7640 2.4336 2.4901
连续统去除光谱Continuum removal spectrum (CRS) 0.7352 0.7576 2.4980 2.5404
KNN 原始光谱Original spectrum (OS) 0.7201 0.7165 2.5300 2.8296
一阶导数光谱First derivative spectrum (FDS) 0.7500 0.7501 2.4350 2.5623
连续统去除光谱Continuum removal spectrum (CRS) 0.7198 0.7346 2.5695 2.6582
XGBoost 原始光谱Original spectrum (OS) 0.7892 0.7454 2.2361 2.5866
一阶导数光谱First derivative spectrum (FDS) 0.8156 0.7671 2.0991 2.4490
连续统去除光谱Continuum removal spectrum (CRS) 0.7886 0.7461 2.1655 2.7398
GBDT 原始光谱Original spectrum (OS) 0.7455 0.7432 2.4571 2.5976
一阶导数光谱First derivative spectrum (FDS) 0.7521 0.7713 2.4336 2.4265
连续统去除光谱Continuum removal spectrum (CRS) 0.7583 0.7373 2.4469 2.4995
RR 原始光谱Original spectrum (OS) 0.5577 0.6642 3.3320 2.7835
一阶导数光谱First derivative spectrum (FDS) 0.6025 0.7375 3.1384 2.4982
连续统去除光谱Continuum removal spectrum (CRS) 0.5627 0.6729 3.3303 2.7129
PLSR 原始光谱Original spectrum (OS) 0.6007 0.6984 3.1416 2.6837
一阶导数光谱First derivative spectrum (FDS) 0.6082 0.7333 3.1041 2.5445
连续统去除光谱Continuum removal spectrum (CRS) 0.6232 0.7391 3.0714 2.4592

Fig. 6

Measured vs predicted values for the six machine-learning models Abbreviations are the same as those given in Fig. 3 and Fig. 5. R2: coefficient of determination; RMSE: root mean squared error."

Table 5

Accuracy comparison of two ensemble machine learning models"

模型
Model		 变换光谱
Transform spectrum		 训练集R2
Train R2		 测试集R2
Test R2		 训练集RMSE
Train RMSE		 测试集RMSE
Test RMSE
Voting 原始光谱Original spectrum (OS) 0.7899 0.7608 2.1835 2.5920
一阶导数光谱First derivative spectrum (FDS) 0.8251 0.8152 2.0115 2.1253
连续统去除光谱Continuum removal spectrum (CRS) 0.8236 0.7717 2.0906 2.3304
Stacking 原始光谱Original spectrum (OS) 0.6958 0.7530 2.6865 2.5476
一阶导数光谱First derivative spectrum (FDS) 0.7589 0.7529 2.3907 2.4502
连续统去除光谱Continuum removal spectrum (CRS) 0.7377 0.7459 2.4712 2.6358

Fig. 7

Scatter plots of measured vs predicted values for Voting and Stacking ensemble machine learning models Abbreviations are the same as those given in Fig. 3 and Fig. 5. R2: coefficient of determination; RMSE: root mean squared error."

Fig. 8

Spatial inversion of leaf nitrogen content in forage maize in 2024 using the Voting-FDS model"

[1] 伏桂华, 杨宝良, 张飞, 等. 尿素对全株玉米青贮饲料发酵品质和饲料营养价值的影响. 饲料研究, 2021, 44(14): 117-119.
Fu G H, Yang B L, Zhang F, et al. Effect of urea on fermentation quality and nutritional value of whole corn silage. Feed Res, 2021, 44(14): 117-119 (in Chinese with English abstract).
[2] 赵春江, 薛绪掌, 王秀, 等. 精准农业技术体系的研究进展与展望. 农业工程学报, 2003, 19(4): 7-12.
Zhao C J, Xue X Z, Wang X, et al. Advance and prospects of precision agriculture technology system. Trans CSAE, 2003, 19(4): 7-12 (in Chinese with English abstract).
[3] Liu H Y, Zhu H C, Wang P. Quantitative modelling for leaf nitrogen content of winter wheat using UAV-based hyperspectral data. Int J Remote Sens, 2017, 38: 2117-2134.
doi: 10.1080/01431161.2016.1253899
[4] Li F, Mistele B, Hu Y C, et al. Reflectance estimation of canopy nitrogen content in winter wheat using optimised hyperspectral spectral indices and partial least squares regression. Eur J Agron, 2014, 52: 198-209.
doi: 10.1016/j.eja.2013.09.006
[5] Erdle K, Mistele B, Schmidhalter U. Comparison of active and passive spectral sensors in discriminating biomass parameters and nitrogen status in wheat cultivars. Field Crops Res, 2011, 124: 74-84.
doi: 10.1016/j.fcr.2011.06.007
[6] Li F, Mistele B, Hu Y C, et al. Optimising three-band spectral indices to assess aerial N concentration, N uptake and aboveground biomass of winter wheat remotely in China and Germany. ISPRS J Photogramm Remote Sens, 2014, 92: 112-123.
doi: 10.1016/j.isprsjprs.2014.03.006
[7] 王莉雯, 卫亚星. 植被氮素浓度高光谱遥感反演研究进展. 光谱学与光谱分析, 2013, 33: 2823-2827.
Wang L W, Wei Y X. Progress in inversion of vegetation nitrogen concentration by hyperspectral remote sensing. Spectrosc Spectral Anal, 2013, 33: 2823-2827. (in Chinese with English abstract).
[8] 魏鹏飞, 徐新刚, 李中元, 等. 基于无人机多光谱影像的夏玉米叶片氮含量遥感估测. 农业工程学报, 2019, 35(8): 126-133.
Wei P F, Xu X G, Li Z Y, et al. Remote sensing estimation of nitrogen content in summer maize leaves based on multispectral images of UAV. Trans CSAE, 2019, 35(8): 126-133 (in Chinese with English abstract).
[9] 徐浩聪, 姚波, 王权, 等. 基于叶片反射光谱估测水稻氮营养指数. 中国农业科学, 2021, 54: 4525-4539.
doi: 10.3864/j.issn.0578-1752.2021.21.004
Xu H C, Yao B, Wang Q, et al. Determination of suitable band width for estimating rice nitrogen nutrition index based on leaf reflectance spectra. Sci Agric Sin, 2021, 54: 4525-4539 (in Chinese with English abstract).
doi: 10.3864/j.issn.0578-1752.2021.21.004
[10] 李岚涛, 李静, 明金, 等. 冬油菜叶面积指数高光谱监测最佳波宽与有效波段研究. 农业机械学报, 2018, 49(2): 156-165.
Li L T, Li J, Ming J, et al. Selection optimization of hyperspectral bandwidth and effective wavelength for predicting leaf area index in winter oilseed rape. Trans CSAM, 2018, 49(2): 156-165 (in Chinese with English abstract).
[11] 秦占飞, 常庆瑞, 谢宝妮, 等. 基于无人机高光谱影像的引黄灌区水稻叶片全氮含量估测. 农业工程学报, 2016, 32(23): 77-85.
Qin Z F, Chang Q R, Xie B N, et al. Rice leaf nitrogen content estimation based on hysperspectral imagery of UAV in Yellow River diversion irrigation district. Trans CSAE, 2016, 32(23): 77-85 (in Chinese with English abstract).
[12] Gitelson A A, Peng Y, Arkebauer T J, et al. Relationships between gross primary production, green LAI, and canopy chlorophyll content in maize: implications for remote sensing of primary production. Remote Sens Environ, 2014, 144: 65-72.
doi: 10.1016/j.rse.2014.01.004
[13] Bolton D K, Friedl M A. Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics. Agric For Meteor, 2013, 173: 74-84.
doi: 10.1016/j.agrformet.2013.01.007
[14] Zhang J Y, Liu X, Liang Y, et al. Using a portable active sensor to monitor growth parameters and predict grain yield of winter wheat. Sensors, 2019, 19: 1108.
doi: 10.3390/s19051108
[15] Marang I J, Filippi P, Weaver T B, et al. Machine learning optimised hyperspectral remote sensing retrieves cotton nitrogen status. Remote Sens, 2021, 13: 1428.
doi: 10.3390/rs13081428
[16] 姚霞, 朱艳, 田永超, 等. 小麦叶层氮含量估测的最佳高光谱参数研究. 中国农业科学, 2009, 42: 2716-2725.
Yao X, Zhu Y, Tian Y C, et al. Research of the optimum hyperspectral vegetation indices on monitoring the nitrogen content in wheat leaves. Sci Agric Sin, 2009, 42: 2716-2725 (in Chinese with English abstract).
[17] 王玉娜, 李粉玲, 王伟东, 等. 基于无人机高光谱的冬小麦氮素营养监测. 农业工程学报, 2020, 36(22): 31-39.
Wang Y N, Li F L, Wang W D, et al. Monitoring of winter wheat nitrogen nutrition based on UAV hyperspectral images. Trans CSAE, 2020, 36(22): 31-39 (in Chinese with English abstract).
[18] 刘昌华, 方征, 陈志超, 等. ASD Field Spec3野外便携式高光谱仪诊断冬小麦氮营养. 农业工程学报, 2018, 34(19): 162-169.
Liu C H, Fang Z, Chen Z C, et al. Nitrogen nutrition diagnosis of winter wheat based on ASD Field Spec3. Trans CSAE, 2018, 34(19): 162-169 (in Chinese with English abstract).
[19] Feng L W, Zhang Z, Ma Y C, et al. Alfalfa yield prediction using UAV-based hyperspectral imagery and ensemble learning. Remote Sens, 2020, 12: 2028.
doi: 10.3390/rs12122028
[20] Fu P, Meacham-Hensold K, Guan K Y, et al. Hyperspectral leaf reflectance as proxy for photosynthetic capacities: an ensemble approach based on multiple machine learning algorithms. Front Plant Sci, 2019, 10: 730.
doi: 10.3389/fpls.2019.00730 pmid: 31214235
[21] Healey S P, Cohen W B, Yang Z Q, et al. Mapping forest change using stacked generalization: an ensemble approach. Remote Sens Environ, 2018, 204: 717-728.
doi: 10.1016/j.rse.2017.09.029
[22] Peppes N, Daskalakis E, Alexakis T, et al. Performance of machine learning-based multi-model voting ensemble methods for network threat detection in agriculture 4.0. Sensors, 2021, 21: 7475.
doi: 10.3390/s21227475
[23] 符欣彤, 常庆瑞, 张佑铭, 等. 基于Stacking集成学习的猕猴桃叶片叶绿素含量估算. 干旱地区农业研究, 2023, 41(4): 247-256.
Fu X T, Chang Q R, Zhang Y M, et al. Estimation of kiwifruit leaf chlorophyll content based on Stacking ensemble learning. Agric Res Arid Areas, 2023, 41(4): 247-256 (in Chinese with English abstract).
[24] 鲍士旦. 土壤农化分析(第3版). 北京: 中国农业出版社, 2000.
Bao S D. Soil and Agricultural Chemistry Analysis. 3rd edn. Beijing: China Agriculture Press, 2000 (in Chinese).
[25] 陈树人, 邹华东, 吴瑞梅, 等. 基于高光谱图像技术的稻田苗期杂草稻识别. 农业机械学报, 2013, 44(5): 253-257.
Chen S R, Zou H D, Wu R M, et al. Identification for weedy rice at seeding stage based on hyper-spectral imaging technique. Trans CSAM, 2013, 44(5): 253-257 (in Chinese with English abstract).
[26] 陈晓凯, 李粉玲, 王玉娜, 等. 无人机高光谱遥感估算冬小麦叶面积指数. 农业工程学报, 2020, 36(22): 40-49.
Chen X K, Li F L, Wang Y N, et al. Estimation of winter wheat leaf area index based on UAV hyperspectral remote sensing. Trans CSAE, 2020, 36(22): 40-49 (in Chinese with English abstract).
[27] Grimm R, Behrens T, Märker M, et al. Soil organic carbon concentrations and stocks on Barro Colorado Island: digital soil mapping using Random Forests analysis. Geoderma, 2008, 146: 102-113.
doi: 10.1016/j.geoderma.2008.05.008
[28] 张东彦, 韩宣宣, 林芬芳, 等. 基于多源无人机影像特征融合的冬小麦LAI估算. 农业工程学报, 2022, 38(9): 171-179.
Zhang D Y, Han X X, Lin F F, et al. Estimation of winter wheat leaf area index using multi-source UAV image feature fusion. Trans CSAE, 2022, 38(9): 171-179 (in Chinese with English abstract).
[29] 岳继博, 杨贵军, 冯海宽. 基于随机森林算法的冬小麦生物量遥感估算模型对比. 农业工程学报, 2016, 32(18): 175-182.
Yue J B, Yang G J, Feng H K. Comparative of remote sensing estimation models of winter wheat biomass based on random forest algorithm. Trans CSAE, 2016, 32(18): 175-182 (in Chinese with English abstract).
[30] Cosenza D N, Korhonen L, Maltamo M, et al. Comparison of linear regression, k-nearest neighbour and random forest methods in airborne laser-scanning-based prediction of growing stock. Forestry, 2021, 94: 311-323.
doi: 10.1093/forestry/cpaa034
[31] 何龙. 深入理解XGBoost:高效机器学习算法与进阶. 北京: 机械工业出版社, 2020. pp 100-192.
He L. Understanding XGBoost:Efficient Machine Learning Algorithm and Advanced. Beijing: China Machine Press, 2020. pp 100-192 (in Chinese).
[32] Ma X L, Ding C, Luan S, et al. Prioritizing influential factors for freeway incident clearance time prediction using the gradient boosting decision trees method. IEEE Trans Intell Transp Syst, 2017, 18: 2303-2310.
doi: 10.1109/TITS.2016.2635719
[33] Ji S, Gu C, Xi X B, et al. Quantitative monitoring of leaf area index in rice based on hyperspectral feature bands and ridge regression algorithm. Remote Sens, 2022, 14: 2777.
doi: 10.3390/rs14122777
[34] 王圆圆, 李贵才, 张立军, 等. 利用偏最小二乘回归从冬小麦冠层光谱提取叶片含水量. 光谱学与光谱分析, 2010, 30: 1070-1074.
Wang Y Y, Li G C, Zhang L J, et al. Retrieval of leaf water content of winter wheat from canopy hyperspectral data using partial least square regression. Spectrosc Spectr Anal, 2010, 30: 1070-1074 (in Chinese with English abstract).
[35] 付元元, 王纪华, 杨贵军, 等. 应用波段深度分析和偏最小二乘回归的冬小麦生物量高光谱估算. 光谱学与光谱分析, 2013, 32: 1315-1319.
Fu Y Y, Wang J H, Yang G J, et al. Band depth analysis and partial least square regression based winter wheat biomass estimation using hyperspectral measurements. Spectrosc Spectr Anal, 2013, 32: 1315-1319 (in Chinese with English abstract).
[36] 陈帼, 徐新刚, 杜晓初, 等. 基于PLS和组合预测方法的冬小麦收获指数高光谱估测. 中国农业信息, 2019, 31(2): 28-38.
Chen G, Xu X G, Du X C, et al. Estimation of winter harvest index based on PLS and combined prediction method. China Agric Inform, 2019, 31(2): 28-38 (in Chinese with English abstract).
[37] 邹泽林, 程霞, 刘紫薇, 等. Stacking集成学习模型在森林蓄积量估测中的应用. 湖北林业科技, 2023, 52(4): 52-57.
Zou Z L, Cheng X, Liu Z W, et al. Application of stacking ensemble learning model in forest volume estimation. Hubei Sci Technol, 2023, 52(4): 52-57 (in Chinese with English abstract).
[38] Zou X C, Mõttus M. Sensitivity of common vegetation indices to the canopy structure of field crops. Remote Sens, 2017, 9: 994.
doi: 10.3390/rs9100994
[39] Luo L L, Chang Q R, Gao Y F, et al. Combining different transformations of ground hyperspectral data with unmanned aerial vehicle (UAV) images for anthocyanin estimation in tree peony leaves. Remote Sens, 2022, 14: 2271.
doi: 10.3390/rs14092271
[40] 韩兆迎, 朱西存, 刘庆, 等. 黄河三角洲土壤有机质含量的高光谱反演. 植物营养与肥料学报, 2014, 20: 1545-1552.
Han Z Y, Zhu X C, Liu Q, et al. Hyperspectral inversion models for soil organic matter content in the Yellow River Delta. J Plant Nutr Fert, 2014, 20: 1545-1552 (in Chinese with English abstract).
[41] Ollinger S V. Sources of variability in canopy reflectance and the convergent properties of plants. New Phytol, 2011, 189: 375-394.
doi: 10.1111/j.1469-8137.2010.03536.x pmid: 21083563
[42] Kokaly R F, Asner G P, Ollinger S V, et al. Characterizing canopy biochemistry from imaging spectroscopy and its application to ecosystem studies. Remote Sens Environ, 2009, 113: S78-S91.
doi: 10.1016/j.rse.2008.10.018
[43] Fu Y Y, Yang G J, Pu R L, et al. An overview of crop nitrogen status assessment using hyperspectral remote sensing: current status and perspectives. Eur J Agron, 2021, 124: 126241.
doi: 10.1016/j.eja.2021.126241
[44] 韩兆迎, 朱西存, 王凌, 等. 基于连续统去除法的苹果树冠SPAD高光谱估测. 激光与光电子学进展, 2016, 53(2): 214-223.
Han Z Y, Zhu X C, Wang L, et al. Hyperspectral evaluation of SPAD value of apple tree canopy based on continuum-removed method. Laser Optoelectron Prog, 2016, 53(2): 214-223 (in Chinese with English abstract).
[45] 由明明, 常庆瑞, 田明璐, 等. 基于随机森林回归的油菜叶片SPAD值遥感估算. 干旱地区农业研究, 2019, 37(1): 74-81.
You M M, Chang Q R, Tian M L, et al. Estimation of rapeseed leaf SPAD value based on random forest regression. Agric Res Arid Areas, 2019, 37(1): 74-81 (in Chinese with English abstract).
[46] 李媛媛, 常庆瑞, 刘秀英, 等. 基于高光谱和BP神经网络的玉米叶片SPAD值遥感估算. 农业工程学报, 2016, 32(16): 135-142.
Li Y Y, Chang Q R, Liu X Y, et al. Estimation of maize leaf SPAD value based on hyperspectrum and BP neural network. Trans CSAE, 2016, 32(16): 135-142 (in Chinese with English abstract).
[47] 费帅鹏, 禹小龙, 兰铭, 等. 基于高光谱遥感和集成学习方法的冬小麦产量估测研究. 中国农业科学, 2021, 54: 3417-3427.
doi: 10.3864/j.issn.0578-1752.2021.16.005
Fei S P, Yu X L, Lan M, et al. Research on winter wheat yield estimation based on hyperspectral remote sensing and ensemble learning method. Sci Agric Sin, 2021, 54: 3417-3427 (in Chinese with English abstract).
doi: 10.3864/j.issn.0578-1752.2021.16.005
[48] Masclaux C, Valadier M H, Brugière N, et al. Characterization of the sink/source transition in tobacco (Nicotiana tabacum L.) shoots in relation to nitrogen management and leaf senescence. Planta, 2000, 211: 510-518.
doi: 10.1007/s004250000310 pmid: 11030550
[1] Ma Chen-Ming, Ha Si-Tu-Ya, Chang Hong-Bo, Liang Qing-Tian, You Le, Wu Shang-Rong. Estimation of chlorophyll content in potato leaves based on chlorophyll fluorescence imaging [J]. Acta Agronomica Sinica, 2026, 52(7): 2193-2206.
[2] Jiang Jia-Hui, Jiang Bing-Zhi, Liu Guan-Ming, Wang Zhang-Ying, Tang Chao-Chen. Establishment and optimization of near-infrared spectroscopy models for quality traits of purple-fleshed sweet potato [J]. Acta Agronomica Sinica, 2026, 52(4): 1088-1102.
[3] Yang Yue, Zhang Xin-Xin, He Zeng-Hui, Li Rui-Dong, Pan Yu-Jie, Li Jia-Kang, Du Wei, Xu Da-Yong, Du Jin-Song. Non-destructive prediction and visualization of major chemical components in tobacco leaves using hyperspectral imaging [J]. Acta Agronomica Sinica, 2026, 52(3): 922-935.
[4] ZHOU Ke, CHEN Peng-Fei. Maize SPAD estimation by combining multi-source unmanned aerial vehicle remote sensing data and machine learning methods [J]. Acta Agronomica Sinica, 2025, 51(5): 1389-1399.
[5] WANG Qing-Hua, ZHU Ge-Ge, FANG Wen, LIU Shi-Shi, LU Jian-Wei. Diagnosis of nitrogen and phosphorus nutrient content in rapeseed leaves based on hyperspectral remote sensing [J]. Acta Agronomica Sinica, 2025, 51(5): 1326-1337.
[6] HAO Qi, CHEN Tian-Lu, WANG Fu-Gui, WANG Zhen, BAI Lan-Fang, WANG Yong-Qiang, WANG Zhi-Gang. Estimation of canopy nitrogen concentration in maize based on UAV multi- spectral data and spatial nitrogen heterogeneity [J]. Acta Agronomica Sinica, 2025, 51(1): 189-206.
[7] LIN Fen-Fang, CHEN Xing-Yu, ZHOU Wei-Xun, WANG Qian, ZHANG Dong-Yan. Hyperspectral remote sensing detection of Fusarium head blight in wheat based on the stacked sparse auto-encoder algorithm [J]. Acta Agronomica Sinica, 2023, 49(8): 2275-2287.
[8] MA Jun-Wei, CHEN Peng-Fei, SUN Yi, GU Jian, WANG Li-Juan. Comparing different machine learning methods for maize leaf area index (LAI) prediction using multispectral image from unmanned aerial vehicle (UAV) [J]. Acta Agronomica Sinica, 2023, 49(12): 3364-3376.
[9] FENG Zi-Heng, LI Xiao, DUAN Jian-Zhao, GAO Fei, HE Li, YANG Tian-Chong, RONG Ya-Si, SONG Li, YIN Fei, FENG Wei. Hyperspectral remote sensing monitoring of wheat powdery mildew based on feature band selection and machine learning [J]. Acta Agronomica Sinica, 2022, 48(9): 2300-2314.
[10] LI Jin-Min, CHEN Xiu-Qing, YANG Qi, SHI Liang-Sheng. Deep learning models for estimation of paddy rice leaf nitrogen concentration based on canopy hyperspectral data [J]. Acta Agronomica Sinica, 2021, 47(7): 1342-1350.
[11] LI Zong-Fei,SU Ji-Xia,FEI Cong,LI Yang-Yang,LIU Ning-Ning,DAI Yu-Xiang,ZHANG Kai-Xiang,WANG Kai-Yong,FAN Hua,CHEN Bing. Estimation of total nitrogen content in sugarbeet leaves under drip irrigation based on hyperspectral characteristic parameters and vegetation index [J]. Acta Agronomica Sinica, 2020, 46(4): 557-570.
[12] WU Ya-Peng,HE Li,WANG Yang-Yang,LIU Bei-Cheng,WANG Yong-Hua,GUO Tian-Cai,FENG Wei. Dynamic model of vegetation indices for biomass and nitrogen accumulation in winter wheat [J]. Acta Agronomica Sinica, 2019, 45(8): 1238-1249.
[13] CHEN Jun-Xu, HUANG Shan, FAN Yuan-Fang, WANG Rui, LIU Qin-Lin, YANG Wen-Yu*,YANG Feng*. Remote Detection of Canopy Leaf Nitrogen Status in Soybean by Hyperspectral Data under Monoculture and Intercropping Systems [J]. Acta Agron Sin, 2017, 43(12): 1835-1844.
[14] GAO Lin,YANG Gui-Jun,LI Chang-Chun,FENG Hai-Kuan,XU Bo,WANG Lei,DONG Jin-Hui,FU Kui. Application of an Improved Method in Retrieving Leaf Area Index Combined Spectral Index with PLSR in Hyperspectral Data Generated by Unmanned Aerial Vehicle Snapshot Camera [J]. Acta Agron Sin, 2017, 43(04): 549-557.
[15] QI Bo,ZHANG Ning,ZHAO Tuan-Jie,XING Guang-Nan,ZHAO Jing-Ming*,GAI Jun-Yi*. Prediction of Leaf Area Index Using Hyperspectral Remote Sensing in Breeding Programs of Soybean [J]. Acta Agron Sin, 2015, 41(07): 1073-1085.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] Li Shaoqing, Li Yangsheng, Wu Fushun, Liao Jianglin, Li Damo. Optimum Fertilization and Its Corresponding Mechanism under Complete Submergence at Booting Stage in Rice[J]. Acta Agronomica Sinica, 2002, 28(01): 115 -120 .
[2] Wang Lanzhen;Mi Guohua;Chen Fanjun;Zhang Fusuo. Response to Phosphorus Deficiency of Two Winter Wheat Cultivars with Different Yield Components[J]. Acta Agron Sin, 2003, 29(06): 867 -870 .
[3] YANG Jian-Chang;ZHANG Jian-Hua;WANG Zhi-Qin;ZH0U Qing-Sen. Changes in Contents of Polyamines in the Flag Leaf and Their Relationship with Drought-resistance of Rice Cultivars under Water Deficiency Stress[J]. Acta Agron Sin, 2004, 30(11): 1069 -1075 .
[4] Yan Mei;Yang Guangsheng;Fu Tingdong;Yan Hongyan. Studies on the Ecotypical Male Sterile-fertile Line of Brassica napus L.Ⅲ. Sensitivity to Temperature of 8-8112AB and Its Inheritance[J]. Acta Agron Sin, 2003, 29(03): 330 -335 .
[5] Wang Yongsheng;Wang Jing;Duan Jingya;Wang Jinfa;Liu Liangshi. Isolation and Genetic Research of a Dwarf Tiilering Mutant Rice[J]. Acta Agron Sin, 2002, 28(02): 235 -239 .
[6] WANG Li-Yan;ZHAO Ke-Fu. Some Physiological Response of Zea mays under Salt-stress[J]. Acta Agron Sin, 2005, 31(02): 264 -268 .
[7] TIAN Meng-Liang;HUNAG Yu-Bi;TAN Gong-Xie;LIU Yong-Jian;RONG Ting-Zhao. Sequence Polymorphism of waxy Genes in Landraces of Waxy Maize from Southwest China[J]. Acta Agron Sin, 2008, 34(05): 729 -736 .
[8] HU Xi-Yuan;LI Jian-Ping;SONG Xi-Fang. Efficiency of Spatial Statistical Analysis in Superior Genotype Selection of Plant Breeding[J]. Acta Agron Sin, 2008, 34(03): 412 -417 .
[9] WANG Yan;QIU Li-Ming;XIE Wen-Juan;HUANG Wei;YE Feng;ZHANG Fu-Chun;MA Ji. Cold Tolerance of Transgenic Tobacco Carrying Gene Encoding Insect Antifreeze Protein[J]. Acta Agron Sin, 2008, 34(03): 397 -402 .
[10] ZHENG Xi;WU Jian-Guo;LOU Xiang-Yang;XU Hai-Ming;SHI Chun-Hai. Mapping and Analysis of QTLs on Maternal and Endosperm Genomes for Histidine and Arginine in Rice (Oryza sativa L.) across Environments[J]. Acta Agron Sin, 2008, 34(03): 369 -375 .
Add: No. 80 Xueyuan South Rd, Beijing 100081, P. R. China E-mail: zwxb301@caas.cn
Supported by Beijing Magtech Co.Ltd