基于无人机高光谱的马铃薯冠层叶片全氮含量反演

doi:10.3969/j.issn.1004-1524.20221475

浙江农业学报 ›› 2023, Vol. 35 ›› Issue (8): 1904-1914.DOI: 10.3969/j.issn.1004-1524.20221475

基于无人机高光谱的马铃薯冠层叶片全氮含量反演

郭发旭(), 冯全^*(), 杨森, 杨婉霞

甘肃农业大学机电工程学院,甘肃兰州 730070

收稿日期:2022-10-24 出版日期:2023-08-25 发布日期:2023-08-29
作者简介:郭发旭(1997—),男,甘肃永昌人,硕士研究生,主要从事遥感图像处理研究。E-mail:guofax@gsau.edu.cn
通讯作者: *冯全,E-mail:fquan@sina.com
基金资助:
国家自然科学基金(32160421);甘肃省教育厅产业支撑项目(2021CYZC-57);甘肃省优秀研究生“创新之星”项目(2022CXZXS-012);甘肃省高等学校青年博士基金(2021QB-033);甘肃省青年科技基金(20JR10RA544)

Inversion of leaf nitrogen content in potato canopy based on unmanned aerial vehicle hyperspectral images

GUO Faxu(), FENG Quan^*(), YANG Sen, YANG Wanxia

Mechanical and Electrical Engineering College, Gansu Agriculture University, Lanzhou 730070, China

Received:2022-10-24 Online:2023-08-25 Published:2023-08-29

摘要/Abstract

摘要：

为实现大田马铃薯冠层叶片全氮含量(LNC)的快速反演,利用低空无人机平台搭载成像光谱仪获取马铃薯冠层光谱数据,在综合比较原始反射率(R)、倒数变换反射率(1/R)、一阶微分变换反射率[D(R)]、二阶微分变换反射率[D(2R)]、倒数之对数变换反射率[lg(1/R)]的基础上,选择[D(2R)]用于后续试验。分别使用相关性分析(CA)、竞争性自适应重加权(CARS)、无信息变量消除(UVE)3种算法筛选特征光谱波段,使用偏最小二乘回归(PLSR)、支持向量机(SVM)构建马铃薯冠层LNC估测模型。结果表明:CA、CARS、UVE算法分别筛选出26、12、19个特征波段。在构建的PLSR模型中,用UVE筛选的特征波段建立的预测模型[UVE-D(2R)-PLSR]效果最好,在验证集上的决定系数(R²)和均方根误差(RMSE)分别为0.806 8和0.193 2;在构建的SVM模型中,用CARS筛选的特征波段建立的预测模型[CARS-D(2R)-SVM]效果最好,在验证集上的R²和RMSE分别为0.831 6和0.183 0。两模型对比,CARS-D(2R)-SVM模型的效果更好。采用CARS-D(2R)-SVM模型逐点估算马铃薯冠层LNC,绘制反演图,可使种植者直观掌握大田马铃薯生长情况,为马铃薯大田的精细化管理提供数据支持。

关键词: 无人机, 高光谱, 马铃薯, 支持向量机, 反演

Abstract:

To realize the rapid inversion of leaf nitrogen content (LNC) in the canopy of field potatoes, the spectral data of potato canopy leaves were obtained by an imaging spectrometer of a low-altitude unmanned aerial vehicle (UAV) platform. Based on the comprehensive comparison of original reflectance (R), reciprocal transformation reflectance (1/R), first-order differential transformation reflectance [D(R)], second-order differential transformation reflectance [D(2R)], and logarithm of reciprocal transformation reflectance [lg(1/R)], [D(2R)] was selected for the subsequent experiment. Correlation analysis (CA), competitive adaptive reweighed sampling (CARS) and uninformative variables elimination (UVE) algorithms were introduced to screen the characteristic spectral bands, and partial least squares regression (PLSR) and support vector machine (SVM) algorithms were used to construct the LNC estimation model. It was shown that 26, 12 and 19 characteristic bands were screened out by CA, CARS and UVE algorithms, respectively. Among all the established PLSR models, the one based on characteristic bands sreend out by UVE [UVE-D(2R)-PLSR for short] had the best performace, as its determinatino coefficient (R²) and root mean square error (RMSE) on the validatin set were 0.806 8 and 0.193 2, respectively. Among all the established SVM models, the one based on characteristic bands screened out by CARS [CARS-D(2R)-SVM for short] had the best performance, as its R² and RMSE on the validation set were 0.831 6 and 0.183 0, respectively. Compared with UVE-D(2R)-PLSR, CARS-D(2R)-SVM showed better modeling effect. The constructed CARS-D(2R)-SVM model was used to estimate LNC based on the spectral image of potato canopy, and the inverse diagram of LNC was plotted, which could help the growers intuitively grasp the potato growth in the field and provide data support for the potato field management.

Key words: unmanned aerial vehicles, hyperspectrum, potato, support vector machine, inversion

中图分类号:

S127

郭发旭, 冯全, 杨森, 杨婉霞. 基于无人机高光谱的马铃薯冠层叶片全氮含量反演[J]. 浙江农业学报, 2023, 35(8): 1904-1914.

GUO Faxu, FENG Quan, YANG Sen, YANG Wanxia. Inversion of leaf nitrogen content in potato canopy based on unmanned aerial vehicle hyperspectral images[J]. Acta Agriculturae Zhejiangensis, 2023, 35(8): 1904-1914.

图/表 12

表1 样本的冠层叶片全氮含量(LNC)统计值

Table 1 Statistics of leaf nitrogen content (LNC) of samples

样本类型 Sample category	样本数量 Sample size	LNC/%
样本类型 Sample category	样本数量 Sample size	最大值 Maximum value	最小值 Minimum value	平均值 Mean value	标准偏差 Standard deviation
总样本Whole set	110	4.850 0	2.580 0	3.960 5	0.531 6
建模集Calibration set	73	4.850 0	2.720 0	3.967 4	0.524 5
验证集Validation set	37	4.790 0	2.580 0	3.946 8	0.545 1

图1 原始光谱与经过变换的光谱反射率曲线 R,原始光谱;1/R,取倒数;D(R),取一阶微分;D(2R),取二阶微分;lg(1/R),取倒数之常用对数。

Fig.1 Spectral reflectance curves before and after transformation R, Raw; 1/R, Reciprocal; D(R), First-order differential; D(2R), Second-order differential; lg(1/R), Common logarithm of reciprocal value.

表2 基于原始光谱与经过变换的光谱反射率曲线构建的模型效果对比

Table 2 Comparison of modeling effects based on spectral reflectance curves before and after transformation

数据 Data	PLSR		SVM
数据 Data	R²	RMSE	R²	RMSE
R	0.672 0	0.300 4	0.713 1	0.281 3
1/R	0.638 0	0.320 9	0.704 9	0.291 0
D(R)	0.733 6	0.270 8	0.701 3	0.290 1
D(2R)	0.856 9	0.201 7	0.777 2	0.268 0
lg(1/R)	0.642 5	0.313 7	0.721 0	0.277 5

图2 叶片LNC与D(2R)的相关系数

Fig.2 Correlation coefficient between LNC and D(2R)

图3 竞争性自适应重加权(CARS)算法的运行结果 a,变量个数与采样运行次数的关系;b,交叉验证的均方根误差(RMSECV)与采样运行次数的关系;c,回归系数与采样运行次数的关系,“*”表示回归系数最小时所对应的采样次数,不同颜色的曲线代表不同光谱变量回归系数的变化情况。

Fig.3 Running results of competitive adaptive reweighted sampling (CARS) algorithm a, The relationship between the number of variables and the number of sampling runs; b, The relationship between the root mean square error of cross-validation (RMSECV) and the number of sampling runs; c, The relationship between regression coefficient and the number of sampling runs, in which the column marked with an asterisk (*) indicates the number of sampling runs associated with the minimum regression coefficient, and the various colored curves reflect the fluctuations in regression coefficients of distinct spectral variables.

图4 无信息变量消除(UVE)算法的运行结果

Fig.4 Running results of uninformative variables elimination (UVE) algorithm

表3 特征波段筛选结果

Table 3 Characteristic band screening result

方法 Method	特征波段数 Characteristic band number	特征波长 Characteristic wavelength/nm
CA	26	643.8、647.3、640.3、654.2、650.7、657.7、592.0、633.4、636.8、588.6、595.5、571.5、661.2、568.1、585.2、470.6、473.9、699.7、703.3、692.7、696.2、564.7、520.7、517.4、514.0、689.2
CARS	12	431.0、557.9、592.0、633.4、657.7、668.2、682.2、735.1、738.6、749.3、788.7、810.3
UVE	19	557.9、581.8、592.0、602.3、633.4、643.8、647.3、654.2、657.7、668.2、678.7、682.2、731.5、738.6、770.8、788.7、835.7、890.6、901.7

表4 基于不同波段的PLSR建模结果比较

Table 4 Comparison of PLSR modeling results based on different bands

波段 Band	特征波段数量 Number of characteristic bands	建模集Calibration set		验证集Validation set
波段 Band	特征波段数量 Number of characteristic bands	R²	RMSE	R²	RMSE
D(2R)全波段Whole bands of D(2R)	176	0.856 9	0.201 7	0.712 0	0.235 8
CA-D(2R)	26	0.669 7	0.306 5	0.699 3	0.241 0
CARS-D(2R)	12	0.825 4	0.222 9	0.783 9	0.204 3
UVE-D(2R)	19	0.780 1	0.250 1	0.806 8	0.193 2

图5 基于UVE-D(2R)构建的PLSR模型的验证结果

Fig.5 Validation of constructed PLSR model based on UVE-D(2R)

表5 基于不同波段的SVM建模结果比较

Table 5 Comparison of SVM modeling results based on different bands

波段 Band	C	λ	ε	特征波段数量 Number of characteristic bands	建模集Calibration set		验证集Validation set
波段 Band	C	λ	ε	特征波段数量 Number of characteristic bands	R²	RMSE	R²	RMSE
D(2R)全波段	1	0.002 76	0.01	176	0.777 2	0.268 0	0.618 7	0.342 0
Whole bands of D(2R)
CA-D(2R)	4	0.001 95	0.01	26	0.687 6	0.299 8	0.708 4	0.240 6
CARS-D(2R)	91	0.001 95	0.01	12	0.839 0	0.215 2	0.831 6	0.183 0
UVE-D(2R)	512	0.000 98	0.01	19	0.852 6	0.205 4	0.786 9	0.206 2

图6 基于CARS-D(2R)构建的SVM模型的验证结果

Fig.6 Validation of constructed SVM model based on CARS-D(2R)

图7 2021-07-28(a)和2021-08-19(b)马铃薯冠层的LNC反演估测图

Fig.7 Inversion and estimation of potato canopy LNC on 2021-07-28 (a) and 2021-08-19 (b)

参考文献 32

[1]	宋娜, 王凤新, 杨晨飞, 等. 水氮耦合对膜下滴灌马铃薯产量、品质及水分利用的影响[J]. 农业工程学报, 2013, 29(13): 98-105.
	SONG N, WANG F X, YANG C F, et al. Coupling effects of water and nitrogen on yield, quality and water use of potato with drip irrigation under plastic film mulch[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(13): 98-105. (in Chinese with English abstract)
[2]	TANG J Z, XIAO D P, WANG J, et al. Optimizing water and nitrogen managements for potato production in the agro-pastoral ecotone in North China[J]. Agricultural Water Management, 2021, 253: 106945.
[3]	WANG N, REIDSMA P, PRONK A A, et al. Can potato add to China’s food self-sufficiency?: the scope for increasing potato production in China[J]. European Journal of Agronomy, 2018, 101: 20-29.
[4]	FENG W, YAO X, ZHU Y, et al. Monitoring leaf nitrogen status with hyperspectral reflectance in wheat[J]. European Journal of Agronomy, 2008, 28(3): 394-404.
[5]	ZHAO C J, WANG Z J, WANG J H, et al. Relationships of leaf nitrogen concentration and canopy nitrogen density with spectral features parameters and narrow-band spectral indices calculated from field winter wheat (Triticum aestivum L.) spectra[J]. International Journal of Remote Sensing, 2012, 33(11): 3472-3491.
[6]	ZHANG X, SUN H, QIAO X X, et al. Hyperspectral estimation of canopy chlorophyll of winter wheat by using the optimized vegetation indices[J]. Computers and Electronics in Agriculture, 2022, 193: 106654.
[7]	陈仲新, 任建强, 唐华俊, 等. 农业遥感研究应用进展与展望[J]. 遥感学报, 2016, 20(5): 748-767.
	CHEN Z X, REN J Q, TANG H J, et al. Progress and perspectives on agricultural remote sensing research and applications in China[J]. Journal of Remote Sensing, 2016, 20(5): 748-767. (in Chinese with English abstract)
[8]	DELAVARPOUR N, KOPARAN C, NOWATZKI J, et al. A technical study on UAV characteristics for precision agriculture applications and associated practical challenges[J]. Remote Sensing, 2021, 13(6): 1204.
[9]	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[J]. 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[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(22): 31-39. (in Chinese with English abstract)
[10]	张瑶, 郑立华, 李民赞, 等. 基于光谱特征分析的苹果树叶片营养素预测模型构建[J]. 农业工程学报, 2013, 29(8): 171-178.
	ZHANG Y, ZHENG L H, LI M Z, et al. Construction of apple tree leaves nutrients prediction model based on spectral analysis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(8): 171-178. (in Chinese with English abstract)
[11]	李金梦, 叶旭君, 王巧男, 等. 高光谱成像技术的柑橘植株叶片含氮量预测模型[J]. 光谱学与光谱分析, 2014, 34(1): 212-216.
	LI J M, YE X J, WANG Q N, et al. Development of prediction models for determining N content in citrus leaves based on hyperspectral imaging technology[J]. Spectroscopy and Spectral Analysis, 2014, 34(1): 212-216. (in Chinese with English abstract)
[12]	张筱蕾, 刘飞, 聂鹏程, 等. 高光谱成像技术的油菜叶片氮含量及分布快速检测[J]. 光谱学与光谱分析, 2014, 34(9): 2513-2518.
	ZHANG X L, LIU F, NIE P C, et al. Rapid detection of nitrogen content and distribution in oilseed rape leaves based on hyperspectral imaging[J]. Spectroscopy and Spectral Analysis, 2014, 34(9): 2513-2518. (in Chinese with English abstract)
[13]	于雷, 章涛, 朱亚星, 等. 基于IRIV算法优选大豆叶片高光谱特征波长变量估测SPAD值[J]. 农业工程学报, 2018, 34(16): 148-154.
	YU L, ZHANG T, ZHU Y X, et al. Determination of soybean leaf SPAD value using characteristic wavelength variables preferably selected by IRIV algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(16): 148-154. (in Chinese with English abstract)
[14]	吴伟斌, 李佳雨, 张震邦, 等. 基于高光谱图像的茶树LAI与氮含量反演[J]. 农业工程学报, 2018, 34(3): 195-201.
	WU W B, LI J Y, ZHANG Z B, et al. Estimation model of LAI and nitrogen content in tea tree based on hyperspectral image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(3): 195-201. (in Chinese with English abstract)
[15]	李粉玲, 常庆瑞. 基于连续统去除法的冬小麦叶片全氮含量估算[J]. 农业机械学报, 2017, 48(7): 174-179.
	LI F L, CHANG Q R. Estimation of winter wheat leaf nitrogen content based on continuum removed spectra[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(7): 174-179. (in Chinese with English abstract)
[16]	张银杰, 王磊, 白由路, 等. 基于高光谱分析的玉米叶片氮含量分层诊断研究[J]. 光谱学与光谱分析, 2019, 39(9): 2829-2835.
	ZHANG Y J, WANG L, BAI Y L, et al. Nitrogen nutrition diagnostic based on hyperspectral analysis about different layers leaves in maize[J]. Spectroscopy and Spectral Analysis, 2019, 39(9): 2829-2835. (in Chinese with English abstract)
[17]	ZHAO B, DUAN A W, ATA-UL-KARIM S T, et al. Exploring new spectral bands and vegetation indices for estimating nitrogen nutrition index of summer maize[J]. European Journal of Agronomy, 2018, 93: 113-125.
[18]	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[J]. 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[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(23): 77-85. (in Chinese with English abstract)
[19]	李岚涛, 马驿, 魏全全, 等. 基于高光谱的冬油菜植株氮素积累量监测模型[J]. 农业工程学报, 2015, 31(20): 147-156.
	LI L T, MA Y, WEI Q Q, et al. Monitoring models of plant N accumulation of winter oilseed rape based on hyperspectral technology[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(20): 147-156. (in Chinese with English abstract)
[20]	GOFFART J P, OLIVIER M, FRANKINET M. Potato crop nitrogen status assessment to improve N fertilization management and efficiency: past-present-future[J]. Potato Research, 2008, 51(3): 355-383.
[21]	孙伟, 王虎存, 赵武云, 等. 残膜回收型全膜覆土垄播马铃薯挖掘机设计与试验[J]. 农业机械学报, 2018, 49(9): 105-114.
	SUN W, WANG H C, ZHAO W Y, et al. Design and experiment of potato digger with waste film recollection for complete film mulching, soil covering and ridge sowing pattern[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(9): 105-114. (in Chinese with English abstract)
[22]	刘善梅, 李小昱, 钟雄斌, 等. 基于高光谱成像技术的生鲜猪肉含水率无损检测[J]. 农业机械学报, 2013, 44(S1): 165-170.
	LIU S M, LI X Y, ZHONG X B, et al. Non-destructive detection of water content in fresh pork based on hyperspectral imaging technology[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(S1): 165-170. (in Chinese with English abstract)
[23]	郑涛, 刘宁, 孙红, 等. 基于高光谱成像的马铃薯叶片叶绿素分布可视化研究[J]. 农业机械学报, 2017, 48(S1): 153-159.
	ZHENG T, LIU N, SUN H, et al. Visualization of chlorophyll distribution of potato leaves based on hyperspectral imaging technology[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(S1): 153-159. (in Chinese with English abstract)
[24]	MOROS J, KULIGOWSKI J, QUINTÁS G, et al. New cut-off criterion for uninformative variable elimination in multivariate calibration of near-infrared spectra for the determination of heroin in illicit street drugs[J]. Analytica Chimica Acta, 2008, 630(2): 150-160.
[25]	刘云宏, 王庆庆, 石晓微, 等. 金银花贮藏过程中绿原酸含量的高光谱无损检测模型研究[J]. 农业工程学报, 2019, 35(13): 291-299.
	LIU Y H, WANG Q Q, SHI X W, et al. Hyperspectral nondestructive detection model of chlorogenic acid content during storage of honeysuckle[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(13): 291-299. (in Chinese with English abstract)
[26]	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[J]. Geoderma, 2008, 146(1/2): 102-113.
[27]	SURENDRAN U, SANDEEP O, JOSEPH E J. The impacts of magnetic treatment of irrigation water on plant, water and soil characteristics[J]. Agricultural Water Management, 2016, 178: 21-29.
[28]	冯海宽, 杨福芹, 杨贵军, 等. 基于特征光谱参数的苹果叶片叶绿素含量估算[J]. 农业工程学报, 2018, 34(6): 182-188.
	FENG H K, YANG F Q, YANG G J, et al. Estimation of chlorophyll content in apple leaves base on spectral feature parameters[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(6): 182-188. (in Chinese with English abstract)
[29]	YU K, LI F, GNYP M L, et al. Remotely detecting canopy nitrogen concentration and uptake of paddy rice in the Northeast China Plain[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 78: 102-115.
[30]	马怡茹, 吕新, 易翔, 等. 基于机器学习的棉花叶面积指数监测[J]. 农业工程学报, 2021, 37(13): 152-162.
	MA Y R, LYU X, YI X, et al. Monitoring of cotton leaf area index using machine learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(13): 152-162. (in Chinese with English abstract)
[31]	郭阳, 郭俊先, 史勇, 等. CARS-SVM预测哈密瓜可溶性固形物含量[J]. 食品与机械, 2021, 37(6): 81-85.
	GUO Y, GUO J X, SHI Y, et al. Prediction of soluble solids in Hami melon by CARS-SVM[J]. Food & Machinery, 2021, 37(6): 81-85. (in Chinese with English abstract)
[32]	韩康, 于静, 石晓华, 等. 不同光谱指数反演马铃薯叶片氮累积量的研究[J]. 作物学报, 2020, 46(12): 1979-1990.
	HAN K, YU J, SHI X H, et al. Inversion of nitrogen accumulation in potato leaf with different spectral indices[J]. Acta Agronomica Sinica, 2020, 46(12): 1979-1990. (in Chinese with English abstract)

基于无人机高光谱的马铃薯冠层叶片全氮含量反演

Inversion of leaf nitrogen content in potato canopy based on unmanned aerial vehicle hyperspectral images

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 32

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘国敏, 郑虚, 廖玉娇, 覃叶欣, 覃维治. 嫁接对低温胁迫下马铃薯苗抗寒性的影响[J]. 浙江农业学报, 2025, 37(8): 1615-1623.
[2]	谭海霞, 彭红丽, 王连龙, 魏建梅. 马铃薯健康株与疮痂病株根区土壤微生物群落多样性差异分析[J]. 浙江农业学报, 2025, 37(8): 1743-1754.
[3]	江振蓝, 陈付勋, 罗双飞, 罗烨琴, 沙晋明. 基于多光谱变换和主成分分析的土壤全铁含量随机森林模型反演[J]. 浙江农业学报, 2025, 37(7): 1521-1532.
[4]	程嘉瑜, 陈妙金, 李彤, 孙奇男, 张小斌, 赵懿滢, 朱怡航, 顾清. 基于改进Faster-RCNN网络的无人机遥感影像桃树检测[J]. 浙江农业学报, 2024, 36(8): 1909-1919.
[5]	刘泉东, 孙伟, 张华, 刘小龙, 李辉, 王虎存. 跨越式膜上对行覆土装置设计与覆土性能研究[J]. 浙江农业学报, 2024, 36(5): 1173-1184.
[6]	丛杰, 张悦如, 李禧龙, 潘宇轩, 吕黄珍, 吕程序. 手持式马铃薯干物质含量无损检测装置设计与试验[J]. 浙江农业学报, 2024, 36(4): 943-951.
[7]	刘彦岑, 郭俊先, 郭阳, 史勇, 黄华, 李龙杰, 张振振. 基于数字图像的大田哈密瓜不同时期冠层相对叶绿素含量检测研究[J]. 浙江农业学报, 2024, 36(3): 651-661.
[8]	王宇, 汪泓, 肖玖军, 李可相, 邢丹, 张永亮, 陈阳, 张蓝月. 基于优化植被指数组合的多品种辣椒叶片叶绿素数值估测[J]. 浙江农业学报, 2023, 35(9): 2109-2120.
[9]	张梦, 佘宝, 杨玉莹, 黄林生, 朱梦琦. 基于无人机RGB影像的大豆种植区提取方法研究[J]. 浙江农业学报, 2023, 35(4): 952-961.
[10]	朱永基, 陶新宇, 陈小芳, 苏祥祥, 刘吉凯, 李新伟. 基于无人机多光谱影像植被指数与纹理特征的冬小麦地上部生物量估算[J]. 浙江农业学报, 2023, 35(12): 2966-2976.
[11]	姜友谊, 张成健, 韩少宇, 杨小冬, 杨贵军, 杨浩. 基于无人机三维点云的玉米植株自动计数研究[J]. 浙江农业学报, 2022, 34(9): 2032-2042.
[12]	李文翔, 王芳, 王舰. 马铃薯miR397的克隆及靶基因筛选[J]. 浙江农业学报, 2022, 34(6): 1141-1151.
[13]	王钧, 陆洲, 罗明, 徐飞飞, 张序. 基于机载多光谱的冬小麦返青期土壤墒情反演[J]. 浙江农业学报, 2022, 34(6): 1297-1305.
[14]	李永梅, 王浩, 赵勇, 张立根. 基于连续统去除法的枸杞叶片含水率高光谱估算[J]. 浙江农业学报, 2022, 34(4): 781-789.
[15]	蔡瑶, 缪宇轩, 吴浩, 王丹. 高CO₂浓度下冬小麦的高光谱特征及其与叶面积指数和SPAD值的反演[J]. 浙江农业学报, 2022, 34(3): 582-589.