基于无人机多光谱遥感的早稻二化螟为害程度评价

doi:10.3969/j.issn.1004-1524.20240107

浙江农业学报 ›› 2025, Vol. 37 ›› Issue (3): 603-611.DOI: 10.3969/j.issn.1004-1524.20240107

基于无人机多光谱遥感的早稻二化螟为害程度评价

曹梦娇¹(), 白石², 唐攀攀², 王晔青¹, 徐红星³^,^*(), 周国鑫⁴

1.嘉兴市土肥植保与农村能源站,浙江嘉兴 314100
2.南湖实验室大数据技术研究中心,浙江嘉兴 314100
3.浙江省农业科学院植物保护与微生物研究所,浙江杭州 310021
4.浙江农林大学现代农学院,浙江杭州 311300

收稿日期:2024-01-25 出版日期:2025-03-25 发布日期:2025-04-02
作者简介:曹梦娇(1990—),女,浙江嘉善人,硕士,农艺师,研究方向为农作物病虫害监测与预警。E-mail:1240562399@qq.com
通讯作者: * 徐红星,E-mail:hzxuhongxing@163.com
基金资助:
浙江省重点研发计划(2022C02034);浙江省粮油产业技术项目

Evaluation of damage degree of Chilo suppressalis on early rice based on unmanned aerial vehicle multispectral remote sensing

CAO Mengjiao¹(), BAI Shi², TANG Panpan², WANG Yeqing¹, XU Hongxing³^,^*(), ZHOU Guoxin⁴

1. Jiaxing Soil Fertilizer, Plant Protection and Rural Energy Station, Jiaxing 314100, Zhejiang, China
2. Big Data Technology Research Center, Nanhu Laboratory, Jiaxing 314100, Zhejiang, China
3. Institute of Plant Protection and Microbiology, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, China
4. College of Advanced Agricultural Sciences, Zhejiang A&F University, Hangzhou 311300, China

Received:2024-01-25 Online:2025-03-25 Published:2025-04-02

摘要/Abstract

摘要：

为明确无人机多光谱遥感技术能否用于早稻二化螟为害程度评估,通过喷施不同农药、不同次数来控制二化螟的为害,利用多光谱无人机获取b1(450 nm)、b2(555 nm)、b3(660 nm)、b4(720 nm)、b5(750 nm)、b6(840 nm)波段的反射率数据,记录田间作物生长状态和环境信息,采用线性回归、支持向量机、随机森林、岭回归、Lasso回归和贝叶斯回归等6种机器学习模型,研究了在3个时间段获取的多光谱数据和二化螟为害率的相关性。结果表明,基于双时相(抽穗期、腊熟期)数据的支持向量机模型更能反映二化螟为害信息,预测结果与实际的田间二化螟为害程度相对一致。研究结果初步证实,无人机多光谱遥感结合双时相支持向量机模型可有效评估二化螟的为害程度,可为智慧植保的发展提供一定的理论依据与参考。

关键词: 二化螟, 为害率, 多光谱, 建模

Abstract:

To clarify the applicability of unmanned aerial vehicle (UAV) multispectral remote sensing in the assessment of the damage severity caused by Chilo suppressalis on early rice, diversified damage ratios were artificially created by spraying different pesticides with varying frequencies. The reflectance of 6 bands, namely, b1 (450 nm), b2 (555 nm), b3 (660 nm), b4 (720 nm), b5 (750 nm) and b6 (840 nm) was acquired by utilizing UAV multispectral image, and the crop growth and environmental information were obtained in the field. Six machine learning models, including linear regression, support vector machine, random forest, ridge regression, Lasso regression (least absolute shrinkage and selection operator regression) and Bayesian regression, were employed to establish relationships between the multispectral data acquired during three periods and the determined damage ratio of Chilo suppressalis. It was shown that the support vector machine with two-phase (heading stage and wax ripening stage) data could better reflect the real damage of Chilo suppressalis on early rice, and the predicted result was relatively consistent with the real situation in the field. This study preliminarily proved that the support vector machine with two-phase data obtained by UAV multispectral remote sensing could be used to evaluate the damage degree of Chilo suppressalis on early rice, which could provide theoretical basis and reference for the development of intelligent plant protection.

Key words: Chilo suppressalis, damage ratio, multispectral, modeling

中图分类号:

S431.9

曹梦娇, 白石, 唐攀攀, 王晔青, 徐红星, 周国鑫. 基于无人机多光谱遥感的早稻二化螟为害程度评价[J]. 浙江农业学报, 2025, 37(3): 603-611.

CAO Mengjiao, BAI Shi, TANG Panpan, WANG Yeqing, XU Hongxing, ZHOU Guoxin. Evaluation of damage degree of Chilo suppressalis on early rice based on unmanned aerial vehicle multispectral remote sensing[J]. Acta Agriculturae Zhejiangensis, 2025, 37(3): 603-611.

图/表 6

参考文献 24

[1]	范承啸, 韩俊, 熊志军, 等. 无人机遥感技术现状与应用[J]. 测绘科学, 2009, 34(5): 214-215.
	FAN C X, HAN J, XIONG Z J, et al. Application and status of unmanned aerial vehicle remote sensing technology[J]. Science of Surveying and Mapping, 2009, 34(5): 214-215. (in Chinese with English abstract)
[2]	张宏鸣, 谭紫薇, 韩文霆, 等. 基于无人机遥感的玉米株高提取方法[J]. 农业机械学报, 2019, 50(5): 241-250.
	ZHANG H M, TAN Z W, HAN W T, et al. Extraction method of maize height based on UAV remote sensing[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(5): 241-250. (in Chinese with English abstract)
[3]	李广, 张立元, 宋朝阳, 等. 小麦倒伏信息无人机多时相遥感提取方法[J]. 农业机械学报, 2019, 50(4): 211-220.
	LI G, ZHANG L Y, SONG C Y, et al. Extraction method of wheat lodging information based on multi-temporal UAV remote sensing data[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(4): 211-220. (in Chinese with English abstract)
[4]	NIU Y X, ZHANG L Y, ZHANG H H, et al. Estimating above-ground biomass of maize using features derived from UAV-based RGB imagery[J]. Remote Sensing, 2019, 11(11): 1261.
[5]	张玲, 陈新平, 贾良良. 基于无人机可见光遥感的夏玉米氮素营养动态诊断参数研究[J]. 植物营养与肥料学报, 2018, 24(1): 261-269.
	ZHANG L, CHEN X P, JIA L L. Parameter research of using UAV-based visible spectral analysis technology in dynamical diagnosis of nitrogen status of summer maize[J]. Journal of Plant Nutrition and Fertilizers, 2018, 24(1): 261-269. (in Chinese with English abstract)
[6]	高开秀, 高雯晗, 明金, 等. 无人机载多光谱遥感监测冬油菜氮素营养研究[J]. 中国油料作物学报, 2019, 41(2): 232-242.
	GAO K X, GAO W H, MING J, et al. Monitoring of nitrogen nutrition in winter rapeseed using UAV-borne multispectral data[J]. Chinese Journal of Oil Crop Sciences, 2019, 41(2): 232-242. (in Chinese with English abstract)
[7]	ZHANG M N, ZHOU J F, SUDDUTH K A, et al. Estimation of maize yield and effects of variable-rate nitrogen application using UAV-based RGB imagery[J]. Biosystems Engineering, 2020, 189: 24-35.
[8]	田婷, 张青, 张海东, 等. 基于无人机遥感的水稻产量估测[J]. 中国稻米, 2022, 28(1): 67-71.
	TIAN T, ZHANG Q, ZHANG H D, et al. Estimating yield of rice based on remote sensing by unmanned aerial vehicle[J]. China Rice, 2022, 28(1): 67-71. (in Chinese with English abstract)
[9]	闫征远, 范洁茹, 刘伟, 等. 基于田间空气中病菌孢子浓度的小麦白粉病病情估计模型研究[J]. 植物病理学报, 2017, 47(2): 253-261.
	YAN Z Y, FAN J R, LIU W, et al. Models of disease index estimation of wheat powdery mildew based on the concentrations of Blumeria graminis f. sp. tritici conidia in the fields[J]. Acta Phytopathologica Sinica, 2017, 47(2): 253-261. (in Chinese with English abstract)
[10]	严海军, 卓越, 李茂娜, 等. 基于机器学习和无人机多光谱遥感的苜蓿产量预测[J]. 农业工程学报, 2022, 38(11): 64-71.
	YAN H J, ZHUO Y, LI M N, et al. Alfalfa yield prediction using machine learning and UAV multispectral remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(11): 64-71. (in Chinese with English abstract)
[11]	韩文霆, 张立元, 牛亚晓, 等. 无人机遥感技术在精量灌溉中应用的研究进展[J]. 农业机械学报, 2020, 51(2): 1-14.
	HAN W T, ZHANG L Y, NIU Y X, et al. Review on UAV remote sensing application in precision irrigation[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(2): 1-14. (in Chinese with English abstract)
[12]	吴才聪, 胡冰冰, 赵明, 等. 基于无人机影像和半变异函数的玉米螟空间分布预报方法[J]. 农业工程学报, 2017, 33(9): 84-91.
	WU C C, HU B B, ZHAO M, et al. Prediction method for spatial distribution of corn borer based on unmanned aerial vehicle images and semivariance function[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(9): 84-91. (in Chinese with English abstract)
[13]	马书英, 郭增长, 王双亭, 等. 板栗树红蜘蛛虫害无人机高光谱遥感监测研究[J]. 农业机械学报, 2021, 52(4): 171-180.
	MA S Y, GUO Z Z, WANG S T, et al. Hyperspectral remote sensing monitoring of Chinese chestnut red mite insect pests in UAV[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(4): 171-180. (in Chinese with English abstract)
[14]	ABDULRIDHA J, BATUMAN O, AMPATZIDIS Y. UAV-based remote sensing technique to detect citrus canker disease utilizing hyperspectral imaging and machine learning[J]. Remote Sensing, 2019, 11(11): 1373.
[15]	孙钰, 周焱, 袁明帅, 等. 基于深度学习的森林虫害无人机实时监测方法[J]. 农业工程学报, 2018, 34(21): 74-81.
	SUN Y, ZHOU Y, YUAN M S, et al. UAV real-time monitoring for forest pest based on deep learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(21): 74-81. (in Chinese with English abstract)
[16]	BACKOULOU G F, ELLIOTT N C, GILES K, et al. Spatially discriminating Russian wheat aphid induced plant stress from other wheat stressing factors[J]. Computers and Electronics in Agriculture, 2011, 78(2): 123-129.
[17]	崔美娜. 基于无人机遥感的棉花螨害动态监测研究[D]. 石河子: 石河子大学, 2019.
	CUI M N. Study on dynamic monitoring of cotton spider mites based on remote sensing of UAV[D]. Shihezi: Shihezi University, 2019. (in Chinese with English abstract)
[18]	钟雪明, 王晔青, 曹梦娇, 等. 耕作制度演变对水稻螟虫发生为害的影响[J]. 中国植保导刊, 2018, 38(6): 30-35.
	ZHONG X M, WANG Y Q, CAO M J, et al. Impact of farming system development on occurring of rice borers[J]. China Plant Protection, 2018, 38(6): 30-35. (in Chinese)
[19]	KASINATHAN T, SINGARAJU D, UYYALA S R. Insect classification and detection in field crops using modern machine learning techniques[J]. Information Processing in Agriculture, 2021, 8(3): 446-457.
[20]	TUDA M, LUNA-MALDONADO A I. Image-based insect species and gender classification by trained supervised machine learning algorithms[J]. Ecological Informatics, 2020, 60: 101135.
[21]	MARKOVIĆ D, VUJIČIĆ D, TANASKOVIĆ S, et al. Prediction of pest insect appearance using sensors and machine learning[J]. Sensors, 2021, 21(14): 4846.
[22]	汪航, 师茁, 王岩, 等. 基于MODIS时间序列数据的春尺蠖虫害遥感监测方法研究: 以新疆巴楚胡杨为例[J]. 遥感技术与应用, 2018, 33(4): 686-695.
	WANG H, SHI Z, WANG Y, et al. A method for detecting the damage of Apocheima cinerarius erschoff based on MODIS time series: case studies in Bachu Populus euphratica forest of Xinjiang Province[J]. Remote Sensing Technology and Application, 2018, 33(4): 686-695. (in Chinese with English abstract)
[23]	OLSSON P O, LINDSTRÖM J, EKLUNDH L. Near real-time monitoring of insect induced defoliation in subalpine birch forests with MODIS derived NDVI[J]. Remote Sensing of Environment, 2016, 181: 42-53.
[24]	GREENE A D, REAY-JONES F P F, KIRK K R, et al. Spatial associations of key lepidopteran pests with defoliation, NDVI, and plant height in soybean[J]. Environmental Entomology, 2021, 50(6): 1378-1392.

编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%
1	1.39	2	1.67	3	0.69	4	2.36	5	3.16
6	2.22	7	2.78	8	2.78	9	3.19	10	7.92
11	2.08	12	3.47	13	3.61	14	3.75	15	6.81
16	28.33	17	45.14	18	3.19	19	2.78	20	7.36
21	3.61	22	16.53	23	1.81	24	11.53	25	2.92
26	1.25	27	2.08	28	1.67	29	1.11	30	1.94
31	1.81	32	4.03	33	9.44	34	2.22	35	3.06
36	11.67	37	3.33	38	3.33	39	1.25	40	8.33
41	2.78	42	4.03	43	12.22	44	2.36	45	4.03
46	41.60	47	28.30	48	24.60	49	4.60	50	29.60
51	7.60	52	11.50	53	12.50	54	15.70	55	19.70
56	30.20	57	31.60	58	23.90	59	20.00

编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%	编号 No.	为害率 Damage ratio/%
1	1.39	2	1.67	3	0.69	4	2.36	5	3.16
6	2.22	7	2.78	8	2.78	9	3.19	10	7.92
11	2.08	12	3.47	13	3.61	14	3.75	15	6.81
16	28.33	17	45.14	18	3.19	19	2.78	20	7.36
21	3.61	22	16.53	23	1.81	24	11.53	25	2.92
26	1.25	27	2.08	28	1.67	29	1.11	30	1.94
31	1.81	32	4.03	33	9.44	34	2.22	35	3.06
36	11.67	37	3.33	38	3.33	39	1.25	40	8.33
41	2.78	42	4.03	43	12.22	44	2.36	45	4.03
46	41.60	47	28.30	48	24.60	49	4.60	50	29.60
51	7.60	52	11.50	53	12.50	54	15.70	55	19.70
56	30.20	57	31.60	58	23.90	59	20.00

数据 Data	不同时期的相关系数 Correlation coefficients of different periods
数据 Data	2023-07-05	2023-07-11	2023-07-31
b1	0.19	0.02	0.16
b2	0.10	0.05	0.17
b3	0.06	0.08	0.15
b4	0.06	0.09	0.18
b5	0.01	0.04	0.18
b6	0.09	0.16	0.19
NDVI	0.04	0.17	0.24

数据 Data	不同时期的相关系数 Correlation coefficients of different periods
数据 Data	2023-07-05	2023-07-11	2023-07-31
b1	0.19	0.02	0.16
b2	0.10	0.05	0.17
b3	0.06	0.08	0.15
b4	0.06	0.09	0.18
b5	0.01	0.04	0.18
b6	0.09	0.16	0.19
NDVI	0.04	0.17	0.24

回归方法 Regression method	基于三时相数据的相关系数 Correlation coefficient obtained by triple temporal phases data		基于双时相数据的相关系数 Correlation coefficient obtained by double temporal phases data		基于单时相数据的相关系数 Correlation coefficient obtained by single temporal phase data
回归方法 Regression method	训练集 Training set	验证集 Verification set	训练集 Training set	验证集 Verification set	训练集 Training set	验证集 Verification set
线性回归Linear regression	0.88	0.45	0.81	0.45	0.65	0.31
支持向量机Support vector machine	0.70	0.85	0.92	0.94	0.82	0.87
随机森林Random forest	0.92	0.56	0.92	0.42	0.90	0.58
岭回归Ridge regression	0.73	0.60	0.61	0.66	0.72	0.66
Lasso回归	0.40	0.56	0.65	0.66	0.61	0.66
least absolute shrinkage and selection operator (Lasso) regression
贝叶斯回归Bayesian regression	0.72	0.45	0.68	0.48	0.74	0.45

基于无人机多光谱遥感的早稻二化螟为害程度评价

Evaluation of damage degree of Chilo suppressalis on early rice based on unmanned aerial vehicle multispectral remote sensing

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 24

相关文章 15

编辑推荐

Metrics

本文评价

[1]	雷志伟, 李新欣, 徐恒, 张恒, 朱英, 张华. 利用染色体片段替换系鉴定水稻二化螟抗性QTL[J]. 浙江农业学报, 2025, 37(3): 530-537.
[2]	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.
[3]	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.
[4]	鲁艳辉, 郭嘉雯, 田俊策, 薛钊鸿, 郑许松, 吕仲贤. 基于COⅠ和Cytb基因的浙江不同抗性水平二化螟种群的遗传结构分析[J]. 浙江农业学报, 2022, 34(11): 2462-2470.
[5]	朱宇, 刘洋. 二化螟幼虫热胁迫响应的转录组分析[J]. 浙江农业学报, 2020, 32(5): 849-857.
[6]	金秀, 卢杰, 傅运之, 王帅, 许高健, 李绍稳. 基于深度卷积神经网络的小麦赤霉病高光谱病症点分类方法[J]. 浙江农业学报, 2019, 31(2): 315-325.
[7]	王文才, 赵刘, 李绍稳, 齐海军, 金秀, 王帅. 基于特征波长选择和建模的高光谱土壤总氮含量估测方法研究[J]. 浙江农业学报, 2018, 30(9): 1576-1584.
[8]	步正延, 李臻峰, 宋飞虎, 李斌, 李静. 基于太赫兹成像技术的大豆叶片水分含量测定[J]. 浙江农业学报, 2018, 30(8): 1420-1426.
[9]	白琪, 鲁艳辉, 郑许松, 吕仲贤. 二化螟两种P450基因CYP4M38和CYP4M39的时空表达分析[J]. 浙江农业学报, 2018, 30(4): 521-527.
[10]	林贤文;周瀛;赵敏;朱金良;杜永均;程家安;祝增荣;*. 田间高效诱集二化螟雄蛾的性信息素诱芯的筛选[J]. , 2013, 25(5): 0-1042.
[11]	朱金良;祝增荣;*;冯金祥;蔡雪涛;钟雪明;程家安. 水稻播种和移栽期对本地越冬主要病虫害发生的影响[J]. , 2011, 23(2): 0-334.
[12]	童森淼;王品维;孙逸钊;张立钦;*;马建义;盛仙俏 . 喜树碱对稻飞虱、二化螟和蚜虫的杀虫作用评价[J]. , 2009, 21(3): 0-292.
[13]	郑许松;陈建明;陈列忠;张珏锋;郑春龙;俞晓平. 茭白种质资源对二化螟和长绿飞虱的抗性评价[J]. , 2006, 18(5): 0-353.
[14]	徐红星;吕仲贤;陈建明;陈列忠;俞晓平. 雷公藤总生物碱对二化螟的生物活性[J]. , 2006, 18(5): 0-343.
[15]	郑许松;叶恭银;俞晓平;吕仲贤;陈建明;徐红星. 银杏叶粗提物对茭白二化螟的生物活性[J]. , 2003, 15(3): 0-176.