欢迎访问作物学报，今天是
作物学报

作物学报 ›› 2026, Vol. 52 ›› Issue (6): 1788-1801.doi: 10.3724/SP.J.1006.2026.53085

• 耕作栽培·生理生化 • 上一篇    下一篇

基于无人机高光谱和机器学习的旱地饲用玉米叶片氮含量估测

梁进宇**(), 尹嘉德**(), 王红丽, 张国平, 侯慧芝, 董博, 马明生*()   

  1. 甘肃省农业科学院旱地农业研究所 / 甘肃省旱作区水资源高效利用重点实验室 / 农业农村部西北旱地农业绿色低碳重点实验室, 甘肃兰州 730070
  • 收稿日期:2025-10-29 接受日期:2026-02-27 出版日期:2026-06-12 网络出版日期:2026-03-10
  • 通讯作者: * 马明生, E-mail: mamingsh@163.com
  • 作者简介:梁进宇, E-mail: liangjinyu1997@163.com;尹嘉德, E-mail: gsyinjiade@163.com

    **同等贡献

  • 基金资助:
    甘肃省科技计划项目(23JRRA1340);甘肃省科技计划项目(23JRRA1335);甘肃省科技计划项目(24JRRA731);甘肃省农业科学院基础研究计划项目(2026GAAS22-7);国家自然科学基金项目(32360532);陇原青年英才项目

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 Published:2026-06-12 Published online: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

RichHTML

12

PDF

152

摘要：

本研究以无人机高光谱和集成学习结合为切入点, 探索旱地饲用玉米叶片氮含量的最佳光谱估测集成学习模型, 为旱地饲用玉米高效优质生产瓶颈的突破提供参考方法。研究区域位于黄土高原陇中地区, 以饲用玉米为研究对象, 利用无人机搭载V185G一体式云台高光谱成像系统获取数据, 基于原始光谱、一阶导数和连续统去除变换光谱构建任意两波段光谱指数, 结合6种机器学习模型, 构建Voting和Stacking集成学习模型, 建立最优估测模型。结果表明, 变换光谱较原始波段光谱显著提高波段光谱指数与饲用玉米叶片氮含量的相关性。比较6种单一机器学习模型发现, RFR、KNN、XGBoost和GBDT模型在饲用玉米生长阶段表现出较高的精度, 测试集R2为0.7165~0.7713, RMSE为2.4265~2.8296。选用以上4种模型构建Voting和Stacking集成机器学习模型, 模型测试集R2均在0.7459以上, RMSE均在2.6358以下。对以上精度较高的单一机器学习模型进行集成, 发现以一阶导数变换光谱的Voting集成模型精度最高, R2为0.8152, RMSE为2.1253, 表现出更优的预测性能, 提高预测能力和稳定性。Voting-FDS集成模型可以在饲用玉米关键生育期对叶片氮含量进行快速估测, 为田间养分管理和高效优质生产提供理论参考。

关键词: 旱地饲用玉米, 叶片氮含量, 高光谱, 波段选择, 机器学习

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

表1

试验处理描述"

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

表2

航线规划的相机参数"

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

图1

试验区及采样点位置图 该图基于自然资源部标准地图服务网站下载的审图号为GS (2019) 3333号的标准地图制作。底图边界无修改。处理同表1。"

图2

高光谱影像拼接流程 Cuvis Export 3.2为高光谱影像导出软件; Agisoft Metashape为高光谱影像拼接软件; 软件ENVI 5.6将TIFF格式转化为BIL格式。TIFF: 标记图像文件格式; BIL: 行式波段交叉格式。"

图3

集成机器学习流程图 RFR: 随机森林回归; KNN: K近邻回归; XGBoost: 极端梯度提升; GBDT: 梯度提升决策树; RR: 岭回归; PLSR: 偏最小二乘回归; Voting: 投票法; Stacking: 堆叠泛化。"

图4

原始光谱特征"

图5

窄波段光谱指数与饲用玉米叶片氮含量的相关性等势图 OS: 原始光谱; FDS: 一阶导数光谱; CRS: 连续统去除光谱; NDSI: 归一化光谱指数; RSI: 比值光谱指数; DSI: 差值光谱指数。"

表3

窄波段光谱指数的最佳波段组合"

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**

表4

6种机器学习模型精度比较"

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

图6

6种机器学习模型的实测值与预测值拟合图 缩写同图3和图5。R2: 决定系数; RMSE: 均方根误差。"

表5

2种集成机器学习模型精度比较"

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

图7

Voting和Stacking集成机器学习模型的实测值与预测值拟合图 缩写同图3和图5。R2: 决定系数; RMSE: 均方根误差。"

图8

Voting-FDS模型反演2024年饲用玉米叶片氮含量"

[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] 马晨铭, 哈斯图亚, 常泓博, 梁擎天, 游乐, 吴尚蓉. 基于叶绿素荧光成像系统的马铃薯叶片叶绿素含量估测[J]. 作物学报, 2026, 52(7): 2193-2206.
[2] 蒋嘉卉, 江炳志, 刘冠明, 王章英, 唐朝臣. 紫肉甘薯品质性状的近红外光谱预测模型构建与优化[J]. 作物学报, 2026, 52(4): 1088-1102.
[3] 杨月, 张新新, 贺增辉, 李瑞东, 潘昱洁, 李嘉康, 杜薇, 徐大勇, 堵劲松. 基于高光谱成像的烟叶主要化学成分无损检测与可视化[J]. 作物学报, 2026, 52(3): 922-935.
[4] 周科, 陈鹏飞. 耦合多源无人机遥感数据和机器学习方法的玉米SPAD估测[J]. 作物学报, 2025, 51(5): 1389-1399.
[5] 王清华, 朱格格, 方雯, 刘诗诗, 鲁剑巍. 基于高光谱遥感的油菜叶片氮磷养分含量诊断[J]. 作物学报, 2025, 51(5): 1326-1337.
[6] 郝琪, 陈天陆, 王富贵, 王振, 白岚方, 王永强, 王志刚. 基于无人机多光谱数据和氮素空间分异的玉米冠层氮浓度估算[J]. 作物学报, 2025, 51(1): 189-206.
[7] 林芬芳, 陈星宇, 周维勋, 王倩, 张东彦. 基于堆栈稀疏自编码器的小麦赤霉病高光谱遥感检测[J]. 作物学报, 2023, 49(8): 2275-2287.
[8] 马俊伟, 陈鹏飞, 孙毅, 谷健, 王李娟. 基于无人机多光谱影像和机器学习方法的玉米叶面积指数反演研究[J]. 作物学报, 2023, 49(12): 3364-3376.
[9] 冯子恒, 李晓, 段剑钊, 高飞, 贺利, 杨天聪, 戎亚思, 宋莉, 尹飞, 冯伟. 基于特征波段选择和机器学习的小麦白粉病高光谱遥感监测[J]. 作物学报, 2022, 48(9): 2300-2314.
[10] 李金敏, 陈秀青, 杨琦, 史良胜. 基于高光谱的水稻叶片氮含量估计的深度森林模型研究[J]. 作物学报, 2021, 47(7): 1342-1350.
[11] 李宗飞,苏继霞,费聪,李阳阳,刘宁宁,戴宇祥,张开祥,王开勇,樊华,陈兵. 基于高光谱数据的滴灌甜菜叶片全氮含量估算[J]. 作物学报, 2020, 46(4): 557-570.
[12] 吴亚鹏,贺利,王洋洋,刘北城,王永华,郭天财,冯伟. 冬小麦生物量及氮积累量的植被指数动态模型研究[J]. 作物学报, 2019, 45(8): 1238-1249.
[13] 依尔夏提•阿不来提,买买提•沙吾提,白灯莎•买买提艾力,安申群,马春玥. 基于随机森林法的棉花叶片叶绿素含量估算[J]. 作物学报, 2019, 45(1): 81-90.
[14] 高林,杨贵军,李长春,冯海宽,徐波,王磊,董锦绘,付奎. 基于光谱特征与PLSR结合的叶面积指数拟合方法的无人机画幅高光谱遥感应用[J]. 作物学报, 2017, 43(04): 549-557.
[15] 齐波,张宁, 赵团结,邢光南,赵晋铭*,盖钧镒. 利用高光谱技术估测大豆育种材料的叶面积指数[J]. 作物学报, 2015, 41(07): 1073-1085.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 李绍清, 李阳生, 吴福顺, 廖江林, 李达模. 水稻孕穗期在淹涝胁迫下施肥的优化选择及其作用机理[J]. 作物学报, 2002, 28(01): 115 -120 .
[2] 王兰珍;米国华;陈范骏;张福锁. 不同产量结构小麦品种对缺磷反应的分析[J]. 作物学报, 2003, 29(06): 867 -870 .
[3] 杨建昌;张亚洁;张建华;王志琴;朱庆森. 水分胁迫下水稻剑叶中多胺含量的变化及其与抗旱性的关系[J]. 作物学报, 2004, 30(11): 1069 -1075 .
[4] 袁美;杨光圣;傅廷栋;严红艳. 甘蓝型油菜生态型细胞质雄性不育两用系的研究Ⅲ. 8-8112AB的温度敏感性及其遗传[J]. 作物学报, 2003, 29(03): 330 -335 .
[5] 王永胜;王景;段静雅;王金发;刘良式. 水稻极度分蘖突变体的分离和遗传学初步研究[J]. 作物学报, 2002, 28(02): 235 -239 .
[6] 王丽燕;赵可夫. 玉米幼苗对盐胁迫的生理响应[J]. 作物学报, 2005, 31(02): 264 -268 .
[7] 田孟良;黄玉碧;谭功燮;刘永建;荣廷昭. 西南糯玉米地方品种waxy基因序列多态性分析[J]. 作物学报, 2008, 34(05): 729 -736 .
[8] 胡希远;李建平;宋喜芳. 空间统计分析在作物育种品系选择中的效果[J]. 作物学报, 2008, 34(03): 412 -417 .
[9] 王艳;邱立明;谢文娟;黄薇;叶锋;张富春;马纪. 昆虫抗冻蛋白基因转化烟草的抗寒性[J]. 作物学报, 2008, 34(03): 397 -402 .
[10] 郑希;吴建国;楼向阳;徐海明;石春海. 不同环境条件下稻米组氨酸和精氨酸的胚乳和母体植株QTL分析[J]. 作物学报, 2008, 34(03): 369 -375 .
京ICP备15008789号-2