基于无人机多光谱影像的冬小麦SPAD值和氮素值估测研究

doi:10.13733/j.jcam.issn.2095-5553.2025.01.022

摘要/Abstract

摘要： 探究无人机多光谱反演冬小麦SPAD值和氮素值含量的模型估算潜力，采用大疆精灵4多光谱版一体化无人机获得冬小麦返青期与拔节期30m和60m两个高度下的多光谱影像。利用ENVI和ArcGIS软件对图像进行分析处理，与地面采集的叶绿素含量和氮含量进行回归分析。采用线性、非线性、二元、逐步回归、BP神经网络、随机森林回归的方法对植被指数与SPAD值、氮含量建立拟合模型以对叶绿素含量和氮含量进行估测，综合比较返青期与拔节期的数据。研究表明，拔节期数据拟合精度明显高于返青期，30m高度下的植被指数与SPAD值和氮含量通过线性与非线性方法获得的模型拟合精度优于60m，最优模型的决定系数R2分别为0.825和0.813。60m高度下，二元回归分析、逐步回归分析、BP神经网络以及随机森林回归模型中的拟合精度均优于30m，对应两个生长时期的最优模型决定系数R2分别为0.882和0.852、0.891和0.895、0.952和0.949、0.924和0.946。

关键词: 冬小麦, 氮含量, 无人机, SPAD值, BP神经网络

Abstract: In order to explore the model estimation potential of unmanned aerial vehicle （UAV） multispectral inversion of winter wheat SPAD value and nitrogen value content, multispectral images of winter wheat at 30m and 60m height were obtained by DJI Phantom4-M multispectral version. ENVI and ArcGIS software were used to analyze and process the images, and regression analysis was carried out with the chlorophyll content and nitrogen content collected on the ground. In this paper, linear, nonlinear, binary, stepwise regression, BP neural network and random forest regression methods were used to establish a fitting model for vegetation index, SPAD value and nitrogen content to estimate chlorophyll content and nitrogen content, and comprehensively compare the data of greening stage and jointing stage. The results showed that the fitting accuracy of the data in the knotting stage was significantly higher than that in the greening stage. The fitting accuracy of the vegetation index, SPAD value and nitrogen content obtained by linear and nonlinear methods at 30m height was better than that of the model at 60m, and the determination coefficients of the optimal model R2 were 0.825 and 0.813, respectively. At the height of 60m, the fitting accuracy of binary regression analysis, stepwise regression analysis, BP neural network and random forest regression model was better than 30m. The optimal model determination coefficients R2 corresponding to the two growth periods were 0.882 and 0.852, 0.891 and 0.895, 0.952 and 0.949, 0.924 and 0.946, respectively.

Key words: winter wheat, nitrogen content, unmanned aerial vehicle （UAV）, SPAD value, BP neural network

中图分类号:

S226.5

刘冰杰, 苑东豪, 丁力, 李昱岐, 徐一高, 王万章. 基于无人机多光谱影像的冬小麦SPAD值和氮素值估测研究[J]. 中国农机化学报, 2025, 46(1): 144-150.

Liu Bingjie, Yuan Donghao, Ding Li, Li Yuqi, Xu Yigao, Wang Wanzhang. Estimation of SPAD and nitrogen values of winter wheat based on unmanned aerial vehicle multispectral images#br#[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(1): 144-150.

参考文献

［1］　Liu Y, Hatou K, Aihara T, et al. A robust vegetation index based on different UAV RGB images to estimate SPAD values of naked barley leaves ［J］. Remote Sensing, 2021, 13（4）: 686.
［2］　Kanning M, Kühling I, Trautz D, et al. Highresolution UAVbased hyperspectral imagery for LAI and chlorophyll estimations from wheat for yield prediction ［J］. Remote Sensing, 2018, 10（12）: 2000.
［3］　Wang L, Duan Y, Zhang L, et al. Precise estimation of NDVI with a simple NIR sensitive RGB camera and machine learning methods for corn plants ［J］. Sensors, 2020, 20（11）: 3208.
［4］　刘昌华, 王哲, 陈志超, 等. 基于无人机遥感影像的冬小麦氮素监测［J］. 农业机械学报, 2018, 49（6）: 207-214.
Liu Changhua, Wang Zhe, Chen Zhichao, et al. Nitrogen monitoring of winter wheat based on unmanned aerial vehicle remote sensing image ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49（6）: 207-214.
［5］　董超, 赵庚星, 宿宝巍, 等. 基于无人机多光谱影像的冬小麦返青期变量施氮决策模型研究［J］. 光谱学与光谱分析, 2019, 39（11）: 3599-3605.
Dong Chao, Zhao Gengxing, Su Baowei, et al. Decision model of variable nitrogen fertilizer in winter wheat returning green stage based on UAV multispectral images ［J］. Spectroscopy and Spectral Analysis, 2019, 39（11）: 3599-3605.
［6］　刘涛, 张寰, 王志业, 等. 利用无人机多光谱估算小麦叶面积指数和叶绿素含量［J］. 农业工程学报, 2021, 37（19）: 65-72.
Liu Tao, Zhang Huan, Wang Zhiye, et al. Estimation of the leaf area index and chlorophyll content of wheat using UAV multispectrum images ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37（19）: 65-72.
［7］　Rouse J W. Monitoring the vernal advancement of retrogradation （green wave effect） of natural vegetation ［J］. Nasa/gsfc Type Iii. final Report. greenbelt Md, 1974.
［8］　Tucker C J. Red and photographic infrared linear combinations for monitoring vegetation ［J］. Remote Sensing of Environment, 1979, 8（2）: 127-150.
［9］　Jordan C F. Derivation of leafarea index from quality of light on the forest floor ［J］. Ecology, 1969, 50（4）: 663-666.
［10］　Rondeaux G, Steven M, Baret F. Optimization of soiladjusted vegetation indices ［J］. Remote Sensing of Environment, 1996, 55（2）: 95-107.
［11］　Huete A R. A soiladjusted vegetation index （SAVI）［J］. Remote Sensing of Environment, 1988, 25（3）: 295-309.
［12］　牛庆林, 冯海宽, 周新国, 等. 冬小麦SPAD值无人机可见光和多光谱植被指数结合估算［J］. 农业机械学报, 2021, 52（8）: 183-194.
Niu Qinglin, Feng Haikuan, Zhou Xinguo, et al. Combining UAV visible light and multispectral vegetation indices for estimating SPAD value of winter wheat ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52（8）: 183-194.
［13］　Broge N H, Leblanc E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area indexand canopy chlorophyll density ［J］. Remote Sensing of Environment, 2001, 76（2）: 156-172.
［14］　徐云飞, 程琦, 魏祥平, 等. 变异系数法结合优化神经网络的无人机冬小麦长势监测［J］. 农业工程学报, 2021, 37（20）: 71-80.
Xu Yunfei, Cheng Qi, Wei Xiangping, et al. Monitoring of winter wheat growth under UAV using variation coefficient method and optimized neural network ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37（20）: 71-80.
［15］　周敏姑, 邵国敏, 张立元, 等. 无人机多光谱遥感反演冬小麦SPAD值［J］. 农业工程学报, 2020, 36（20）: 125-133.
Zhou Mingu, Shao Guomin, Zhang Liyuan, et al. Inversion of SPAD value of winter wheat by multispectral remote sensing of unmanned aerial vehicles ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36（20）: 125-133.
［16］　李冰, 刘镕源, 刘素红, 等. 基于低空无人机遥感的冬小麦覆盖度变化监测［J］. 农业工程学报, 2012, 28（13）: 160-165.
Li Bing, Liu Rongyuan, Liu Suhong, et al. Monitoring vegetation coverage variation of winter wheat by lowaltitude UAV remote sensing system ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28（13）: 160-165.
［17］　郭伟, 朱耀辉, 王慧芳, 等. 基于无人机高光谱影像的冬小麦全蚀病监测模型研究［J］. 农业机械学报, 2019, 50（9）: 162-169.
Guo Wei, Zhu Yaohui, Wang Huifang, et al. Monitoring model of winter wheat takeall based on UAV hyperspectral imaging ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50（9）: 162-169.
［18］　邓尚奇, 赵钰, 白雪源, 等. 基于无人机图像分割的冬小麦叶绿素与叶面积指数反演［J］. 农业工程学报, 2022, 38（3）: 136-145.
Deng Shangqi, Zhao Yu, Bai Xueyuan, et al. Inversion of chlorophyll and leaf area index for winter wheat based on UAV image segmentation ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38（3）: 136-145.
［19］　Jin X, ZarcoTejada P J, Schmidhalter U, et al. Highthroughput estimation of crop traits: A review of ground and aerial phenoty** platforms ［J］. IEEE Geoscience and Remote Sensing Magazine, 2020, 9（1）: 200-231.
［20］　刘帅兵, 杨贵军, 景海涛, 等. 基于无人机数码影像的冬小麦氮含量反演［J］. 农业工程学报, 2019, 35（11）: 75-85.
Liu Shuaibing, Yang Guijun, Jing Haitao, et al. Retrieval of winter wheat nitrogen content based on UAV digital image ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35（11）: 75-85.

[1]	孙旭, 陈玉兰, 赵达君, 肖彤. 智能化技术采纳对农业生产节本增效的影响研究——以新疆棉田无人机应用为例[J]. 中国农机化学报, 2025, 46(1): 314-322.
[2]	白志坤 , 陈兵 , 高山 , 刘太杰 , 陈子杰 . 农用无人机施药技术应用研究现状[J]. 中国农机化学报, 2024, 45(9): 54-61.
[3]	吴宇通, 张伟, 石文强, 李金阳, 亓立强, . 基于无人机遥感的大豆倒伏识别研究[J]. 中国农机化学报, 2024, 45(9): 209-214.
[4]	黄路生, 彭铭键, 高荣, 文晟, 兰玉彬, 张建桃, . 基于CiteSpace的农药雾滴润湿展布研究进展可视化分析[J]. 中国农机化学报, 2024, 45(8): 69-76.
[5]	陈雨欣, 刘章鑫, 刘欣谊, 刘涛, 孙成明, . 基于机器学习算法的扬州市冬小麦遥感分类提取[J]. 中国农机化学报, 2024, 45(8): 154-161.
[6]	李仁凤, 韩顺凯, 杨风波. 耦合风场四旋翼植保无人机下洗流与雾滴分布研究[J]. 中国农机化学报, 2024, 45(7): 81-86.
[7]	许天富, 赵海燕, 桑维钧, 刘健锋, 谢康, 孙光军. 基于CFD仿真植保无人机在各工况下对施药效果的影响[J]. 中国农机化学报, 2024, 45(7): 87-96.
[8]	窦文豪, 孙三民, 徐鹏翔. 基于Stacking集成学习的枣树智能灌溉系统设计与试验[J]. 中国农机化学报, 2024, 45(6): 270-276.
[9]	罗翔, 曹晓林, 药林桃, 吴罗发, 曹中盛, 舒时富. 基于无人机影像的井冈蜜柚果树树形信息提取及产量估测[J]. 中国农机化学报, 2024, 45(5): 161-167.
[10]	李鹏, 石永康, 万晓燕. 四旋翼农业无人机模块化设计及有限元分析[J]. 中国农机化学报, 2024, 45(5): 210-216.
[11]	林远杨, 王彬, 黄尧, 粟超, 何敬, 刘刚, . 基于无人机影像的N、P对水稻生长的影响[J]. 中国农机化学报, 2024, 45(4): 186-192.
[12]	邱金凯, 许秀英, 康烨, 臧浩, 马锴, 郭志鹏. 基于语义分割的无人机图像西瓜果实提取研究[J]. 中国农机化学报, 2024, 45(3): 182-188.
[13]	赵胜利, , , 王国宾, , , 胡连槟, , , 徐海钰, , , 巩道财, , , 兰玉彬, , . 基于无人机多光谱遥感的棉花生长参数和产量估算[J]. 中国农机化学报, 2024, 45(2): 227-234.
[14]	陈鲁威, , 曾锦, , 袁全春, , 潘健, , 姚凤腾, , 吕晓兰, . 无人机遥感监测果树氮素含量研究进展[J]. 中国农机化学报, 2024, 45(2): 235-243.
[15]	沈德宇, , 陈锋军, , 朱学岩, , 张新伟, 陈闯. 基于无人机航拍与改进YOLOv5s的油茶果实检测[J]. 中国农机化学报, 2024, 45(12): 238-244.