Assessment of nitrogen content in flue-cured tobacco leaves based on UAV-loaded multiple spectrum

doi:10.16178/j.issn.0528-9017.20231115

Abstract

Abstract:

To study the feasibility and effectiveness of multispectral remote sensing technology in field tobacco nitrogen assessment, and to provide an efficient, accurate and non-destructive nitrogen nutrition diagnosis method for large area concentrated tobacco fields, in 2023, field experiments with different treatments were set up in Shiping County. Data on plot multispectral images and tobacco leaf nitrogen content were collected through drone-based multispectral aerial photography and field sampling. Various machine learning algorithms, including multiple linear regression (MLR), partial least squares regression (PLSR), and random forest (RF), were used to construct quantitative relationship models between multispectral characteristics of the tobacco canopy and leaf nitrogen content. The results showed that the model built by MLR had the highest stability, while the model constructed by RF achieved the highest correlation and the lowest error. This study confirms the feasibility of using multispectral remote sensing for diagnosing nitrogen content in field tobacco leaves and has promising results, providing a reference for the remote sensing inversion of more agronomic parameters in tobacco cultivation.

Key words: UAV, flue-cured tobacco, multispectral remote sensing, nitrogen diagnosis, machine learning

CLC Number:

S572

JIN Lei, ZHANG Chi, SHAO Xiaodong, DU Jun, TIAN Jingjing, LIU Yu. Assessment of nitrogen content in flue-cured tobacco leaves based on UAV-loaded multiple spectrum[J]. Journal of Zhejiang Agricultural Sciences, 2025, 66(5): 1158-1162.

Figures/Tables 4

Table 1 Leaf nitrogen content 单位:mg·g-1

数据集	数量	最大值	最小值	平均值	标准差
总样本集	45	44.37	14.48	30.85	8.34
测试集	27	44.37	14.48	30.10	8.23
训练集	18	42.62	17.24	31.99	8.38

Fig.1 Nitrogen content evaluation model of tobacco leaves using MLR

Fig.2 Nitrogen content evaluation model of tobacco leaves using PLSR

Fig.3 Nitrogen content evaluation model of tobacco leaves using RF

References 15

[1]	GU Q, SHENG L, ZHANG T H, et al. Early detection of tomato spotted wilt virus infection in tobacco using the hyperspectral imaging technique and machine learning algorithms[J]. Computers and Electronics in Agriculture, 2019, 167: 105066.
[2]	窦玉青. 基于高光谱技术的烟草含氮化合物估测模型研究[D]. 泰安: 山东农业大学, 2016.
[3]	ZHANG M Z, CHEN T E, GU X H, et al. UAV-borne hyperspectral estimation of nitrogen content in tobacco leaves based on ensemble learning methods[J]. Computers and Electronics in Agriculture, 2023, 211: 108008.
[4]	边琳, 叶飞, 王建雄. 基于无人机低空多光谱遥感监测的烤烟株高研究[J]. 山东农业科学, 2020, 52(12): 126-132.
[5]	王帅, 郭治兴, 梁雪映, 等. 基于无人机多光谱遥感数据的烟草植被指数估产模型研究[J]. 山西农业科学, 2021, 49(2): 195-203.
[6]	叶大鹏, 黄俊昆, 秦华, 等. 基于多光谱与深度学习技术的皱褶初烤烟叶等级识别[J]. 福建农林大学学报(自然科学版), 2022, 51(2): 282-288.
[7]	杨栋淏, 陈成. 基于UAV多光谱遥感的相邻地块烤烟施药对比监测[J]. 现代化农业, 2022(4): 60-62.
[8]	ZHANG R N, ZHANG J Q, KUAI Y, et al. Estimation of tobacco leaf chlorophyll content under different nitrogen levels using UAV-based multispectral camera[C]// International Conference on Agri-Photonics and Smart Agricultural Sensing Technologies (ICASAST 2022). June 10-12, 2022. Zhengzhou, China. SPIE, 2022: 45-49.
[9]	赖佳政, 李贝贝, 程翔, 等. 基于无人机高光谱遥感的烤烟叶片叶绿素含量估测[J]. 智慧农业(中英文), 2023, 5(2): 68-81.
[10]	刘红芸, 吴雪梅, 李德仑, 等. 基于高光谱技术的采摘期烟叶水分含量研究[J]. 中国农机化学报, 2021, 42(9): 157-163.
[11]	孙阳, 李青山, 谭效磊, 等. 鲜烟叶高光谱特征与颜色分析及其关系研究[J]. 中国烟草学报, 2018, 24(4): 55-64.
[12]	李朋彦. 基于无人机高光谱遥感的烤烟生长监测[D]. 郑州: 河南农业大学, 2019.
[13]	LIU N F, TOWNSEND P A, NABER M R, et al. Hyperspectral imagery to monitor crop nutrient status within and across growing seasons[J]. Remote Sensing of Environment, 2021, 255: 112303.
[14]	ZHANG M Z, CHEN T E, GU X H, et al. Hyperspectral remote sensing for tobacco quality estimation, yield prediction, and stress detection: a review of applications and methods[J]. Frontiers in Plant Science, 2023, 14: 1073346.
[15]	贾康, 施文泼. 提高烟草税对CPI和就业的影响与对策[J]. 财经智库, 2020, 5(5): 58-78, 141-142.