基于改进粒子群优化的多生育期烟草LAI估测

doi:10.14088/j.cnki.issn0439-8114.2026.07.032

湖北农业科学 ›› 2026, Vol. 65 ›› Issue (7): 208-214.doi: 10.14088/j.cnki.issn0439-8114.2026.07.032

基于改进粒子群优化的多生育期烟草LAI估测

邓哲红¹, 王薇², 邓时锋¹, 崔国贤², 佘玮², 王帅斌³, 王东³, 曹晓兰¹

1.湖南农业大学信息与智能科学技术学院,长沙 410128;
2.湖南农业大学农学院,长沙 410128;
3.湖南中烟工业有限责任公司技术中心,长沙 410014

收稿日期:2026-04-27 出版日期:2026-07-25 发布日期:2026-07-23
通讯作者: 曹晓兰(1972-）,女,湖南常德人,副教授,博士,主要从事大数据与知识工程与农业信息工程研究工作,（电子信箱）cxl@hunau.net。
作者简介:邓哲红(2000-）,男,湖南岳阳人,在读硕士研究生,研究方向为农业信息化,（电子信箱）wangdayan1@163.com。
基金资助:
国家现代农业产业技术体系项目(CARS-16-E11); 湖南省教育厅重点项目(23A0178); 湖南中烟工业有限责任公司科研开发项目（KY2024YC0015）; 湖南中烟工业有限责任公司科研计划项目（KY2023YC0008）

Estimation of tobacco LAI across multiple growth stages based on improved particle swarm optimization

DENG Zhe-hong¹, WANG Wei², DENG Shi-feng¹, CUI Guo-xian², SHE Wei², WANG Shuai-bin³, WANG Dong³, CAO Xiao-lan¹

1. College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China;
2. College of Agronomy, Hunan Agricultural University, Changsha 410128, China;
3. Technology Center, China Tobacco Hunan Industrial Co., Ltd., Changsha 410014, China

Received:2026-04-27 Published:2026-07-25 Online:2026-07-23

摘要/Abstract

摘要： 为解决烟草叶面积指数（LAI）传统测量效率低、遥感反演特征冗余及模型参数优化易陷入局部最优等问题,构建了适用于不同生育期的烟草LAI估测模型。以烟草团棵期和旺长期为研究对象,基于无人机多光谱影像提取25个遥感变量,并采用竞争自适应重加权采样算法（CARS）、最小角回归算法（LARS）和迭代保留信息变量算法（IRIV）进行特征筛选。结果显示,IRIV算法综合表现较优,可有效降低预测误差;基于优选特征构建随机森林（RF）、XGBoost、BP神经网络和支持向量回归（SVR）模型,其中SVR在基础模型中预测能力最优。进一步引入基于Tent混沌映射改进的粒子群优化算法（TPSO）对SVR模型进行参数寻优,构建TPSO-SVR模型。与PSO-SVR相比,TPSO-SVR模型在团棵期测试集决定系数（R²）提高0.015,达到0.757,均方根误差（RMSE）降低0.006,至0.243;在旺长期测试集R²提高0.021,达到0.872,RMSE降低0.020,至0.253。结果表明,基于IRIV特征筛选与TPSO-SVR模型的分期反演方法可提高烟草关键生育期LAI估测精度,为烟草长势无损监测和田间精准管理提供技术参考。

关键词: 烟草, 叶面积指数, 特征筛选, 混沌序列, 粒子群算法, Tent映射

Abstract: To address the issues of low efficiency in the traditional measurement of tobacco leaf area index (LAI), feature redundancy in remote sensing inversion, and the tendency of model parameter optimization to easily fall into local optima, tobacco LAI estimation models suitable for different growth stages were constructed. The rosette stage and vigorous growth stage of tobacco were taken as the target growth stages, and 25 remote sensing variables were extracted based on unmanned aerial vehicle (UAV) multispectral imagery. Feature selection was conducted using competitive adaptive reweighted sampling (CARS), least angle regression (LARS), and iteratively retains informative variables (IRIV) algorithms. The results demonstrated that the IRIV algorithm exhibited superior comprehensive performance and could effectively reduce prediction errors. Based on the optimally selected features, Random Forest (RF), XGBoost, Back Propagation (BP) neural network, and Support Vector Regression (SVR) models were established, among which the SVR model demonstrated the best baseline predictive capability. Furthermore, a Particle Swarm Optimization algorithm improved by the Tent chaotic map (TPSO) was introduced to optimize the parameters of the SVR model, thereby constructing the TPSO-SVR model. Compared with the PSO-SVR model, the coefficient of determination (R²) of the TPSO-SVR model on the test set at the rosette stage increased by 0.015 to 0.757, and the root mean square error (RMSE) decreased by 0.006 to 0.243; at the vigorous growth stage, the R² on the test set increased by 0.021 to 0.872, and the RMSE decreased by 0.020 to 0.253. The results indicated that the stage-specific inversion method based on IRIV feature selection and the TPSO-SVR model could improve the estimation accuracy of tobacco LAI at key growth stages, providing a technical reference for the non-destructive monitoring of tobacco growth and precision field management.

Key words: tobacco, LAI, feature selection, chaotic sequence, PSO, Tent map

中图分类号:

S127

邓哲红, 王薇, 邓时锋, 崔国贤, 佘玮, 王帅斌, 王东, 曹晓兰. 基于改进粒子群优化的多生育期烟草LAI估测[J]. 湖北农业科学, 2026, 65(7): 208-214.

DENG Zhe-hong, WANG Wei, DENG Shi-feng, CUI Guo-xian, SHE Wei, WANG Shuai-bin, WANG Dong, CAO Xiao-lan. Estimation of tobacco LAI across multiple growth stages based on improved particle swarm optimization[J]. HUBEI AGRICULTURAL SCIENCES, 2026, 65(7): 208-214.

参考文献

[1] 邵小东,蒋样明,王拓,等.基于GLOPEM-CEVSA的烟叶产量遥感监测模型研究[J].中国烟草科学,2022,43(6):95-103.
[2] GARRIGUES S, LACAZE R, BARET F, et al. Validation and intercomparison of global Leaf Area Index products derived from remote sensing data[J]. Journal of geophysical research:Biogeosciences, 2008, 113(G2): 2007JG000635.
[3] 刘忠,万炜,黄晋宇,等.基于无人机遥感的农作物长势关键参数反演研究进展[J].农业工程学报,2018,34(24):60-71.
[4] LAN Y B, HUANG Z X, DENG X L, et al.Comparison of machine learning methods for Citrus greening detection on UAV multispectral images[J]. Computers and electronics in agriculture, 2020, 171: 105234.
[5] 齐浩,孙海芳,吕亮杰,等.基于无人机多光谱信息与纹理特征融合的小麦叶面积指数估测[J].农业机械学报,2025,56(3):334-344.
[6] 游欣妍,蒙继华,林圳鑫,等.烟叶叶面积指数多模型遥感反演的比较研究[J].遥感技术与应用,2025,40(5):1202-1215.
[7] 殷琴亮,刘洋,李建武,等.基于无人机多光谱遥感数据的水稻叶面积指数反演模型研究[J].杂交水稻,2026,41(2):37-47.
[8] BIRU D, GESSESSE B, ABEBE G.Recursive feature elimination for summer wheat leaf area index using ensemble algorithm-based modeling: The case of central Highland of Ethiopia[J]. Environmental challenges, 2025, 19: 101113.
[9] WANG C L, ZHANG X, ZHANG N N, et al.Optimizing the estimation of cotton leaf SPAD and LAI values via UAV multispectral imagery and LASSO regression[J]. Smart agricultural technology, 2025, 12: 101098.
[10] 石浩磊,曹红霞,张伟杰,等.基于无人机多光谱的棉花多生育期叶面积指数反演[J].中国农业科学,2024,57(1):80-95.
[11] LE T S, HARPER R, DELL B.Application of remote sensing in detecting and monitoring water stress in forests[J]. Remote sensing, 2023, 15(13): 3360.
[12] MILLER J R, HARE E W, WU J.Quantitative characterization of the vegetation red edge reflectance 1. An inverted-Gaussian reflectance model[J]. International journal of remote sensing, 1990, 11(10): 1755-1773.
[13] HUETE A, JUSTICE C, LIU H.Development of vegetation and soil indices for MODIS-EOS[J]. Remote sensing of environment, 1994, 49(3): 224-234.
[14] THOMPSON C N, MILLS C, PABUAYON I L B, et al. Time-based remote sensing yield estimates of cotton in water-limiting environments[J]. Agronomy journal, 2020, 112(2): 975-984.
[15] 马俊伟,陈鹏飞,孙毅,等.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.
[16] 于海琳,兰玉彬,李京谦,等.基于无人机遥感数据和机器学习的向日葵LAI反演[J].农业机械学报,2025,56(1):356-365.
[17] RONDEAUX G, STEVEN M, BARET F.Optimization of soil-adjusted vegetation indices[J]. Remote sensing of environment, 1996, 55(2): 95-107.
[18] 王佳丽,蒯雁,杨成伟,等.基于无人机多光谱的烤烟冠层叶绿素含量反演[J].江苏农业科学,2024,52(15):232-238.
[19] 霍迎秋,赵士超,赵国淇,等.基于无人机多光谱的猕猴桃园冠层叶绿素含量检测方法[J].农业机械学报,2024,55(9):297-307.
[20] RICHARDSONS A J,WIEGAND A.Distinguishing vegetation from soil background information[J]. Photogrammetric engineering and remote sensing, 1977, 43: 1541-1552.
[21] DAUGHTRY C S T, GALLO K P, GOWARD S N, et al. Spectral estimates of absorbed radiation and phytomass production in corn and soybean canopies[J]. Remote sensing of environment, 1992, 39(2): 141-152.
[22] GITELSON A A, KAUFMAN Y J, MERZLYAK M N.Use of a green channel in remote sensing of global vegetation from EOS-MODIS[J]. Remote sensing of environment, 1996, 58(3): 289-298.
[23] HABOUDANE D, MILLER J R, PATTEY E, et al.Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture[J]. Remote sensing of environment, 2004, 90(3): 337-352.
[24] 李红军,张立周,陈曦鸣,等.应用数字图像进行小麦氮素营养诊断中图像分析方法的研究[J].中国生态农业学报,2011, 19(1):155-159.
[25] BROGE N H, LEBLANC E.Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density[J]. Remote sensing of environment, 2001, 76(2): 156-172.
[26] KIM M J, YU W H, SONG D J, et al.Prediction of soluble-solid content in Citrus Fruit using visible-near-infrared hyperspectral imaging based on effective-wavelength selection algorithm[J]. Sensors, 2024, 24(5): 1512.
[27] YU Q.Adaptive CoCoLasso for high-dimensional measurement error models[J]. Entropy, 2025, 27(2): 97.
[28] BAI Z J, CHEN S C, HONG Y S, et al.Estimation of soil inorganic carbon with visible near-infrared spectroscopy coupling of variable selection and deep learning in arid region of China[J]. Geoderma, 2023, 437: 116589.
[29] BREIMAN L.Random forests[J]. Machine learning,2001,45(1):5-32.
[30] CHEN T Q, GUESTRIN C.XGBoost: A scalable tree boosting system[A]. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining[C]. San Francisco California USA: ACM, 2016.785-794.
[31] YIN Q, ZHANG Y T, LI W L, et al.Estimation of winter wheat SPAD values based on UAV multispectral remote sensing[J]. Remote Sens, 2023, 15: 3595.
[32] NARMILAN A, GONZALEZ F, SALGADOE A S A, et al. Predicting canopy chlorophyll content in sugarcane crops using machine learning algorithms and spectral vegetation indices derived from UAV multispectral imagery[J]. Remote sensing, 2022, 14(5): 1140.
[33] 赵正强,刘强,马蕊.基于混沌粒子群算法对APSIM-Wheat模型中春小麦产量形成参数的率定分析[J].麦类作物学报,2026,46(4):550-558.
[34] GAO S,WU R,WANG X Y,et al.EFR-CSTP:Encryption for face recognition based on the chaos and semi-tensor product theory[J]. Information sciences, 2023, 621: 766-781.
[35] KHODJAEV S, BOBOJONOV I, KUHN L, et al.Optimizing machine learning models for wheat yield estimation using a comprehensive UAV dataset[J]. Modeling earth systems and environment, 2024, 11(1): 15.

基于改进粒子群优化的多生育期烟草LAI估测

Estimation of tobacco LAI across multiple growth stages based on improved particle swarm optimization

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王大彬, 周显升, 刘志广, 彭富余, 于卫松, 邱军. 基于近红外光谱的烟草品质相似性度量算法构建及应用探究[J]. 湖北农业科学, 2026, 65(5): 172-178.
[2]	张鹏, 张泽志, 游磊, 郑兰兰, 张勇洪. 蒲儿根基因组大小评估与特征分析[J]. 湖北农业科学, 2026, 65(5): 214-220.
[3]	王健, 魏子梦, 刘远上, 丁佳, 曲利利, 薛国喜, 胡静宜, 许春平. 不同包装方式对晾箱过程中片烟温湿度的影响[J]. 湖北农业科学, 2026, 65(4): 202-211.
[4]	程伟, 王辽源, 霍光, 孔伟, 施河丽, 向必坤, 张冉, 董睿婕, 杨兆钰, 曹媛媛, 谭军, 王瑞. 两株生防芽孢杆菌对烟草青枯病的防治效果[J]. 湖北农业科学, 2026, 65(2): 95-100.
[5]	许汝冰, 罗朝鹏, 黎妍妍, 刘俊霞, 杨军, 覃耀. 外源dsRNA介导的RNA干扰靶向沉默CP基因抑制烟草马铃薯Y病毒侵染[J]. 湖北农业科学, 2026, 65(2): 101-106.
[6]	彭宇, 程佳雯, 李彩斌, 马黔, 马玉玺, 何轶, 吴学巧, 周文亮, 邓建强, 齐永霞. 烟草疫霉抗双炔酰菌胺突变株的生物学特性[J]. 湖北农业科学, 2026, 65(2): 120-125.
[7]	陈治宇, 窦世卿. 基于无人机多光谱数据的柑橘叶面积指数反演[J]. 湖北农业科学, 2025, 64(8): 24-30.
[8]	陈涛, 李国兰, 付慧杰, 朱松发, 宋文静, 张亚丽, 于可可. 外源钾肥影响碳氮积累并改善烟草幼苗低温抗性[J]. 湖北农业科学, 2025, 64(7): 36-39.
[9]	袁国议, 李向阳, 刘政宏, 丁从凯, 朱宣全, 白羽祥, 王戈, 王娜, 周鹏, 杜宇, 宋洁. 云南省烟草漂浮育苗用水效率影响因素分析[J]. 湖北农业科学, 2025, 64(5): 105-111.
[10]	赵子佳, 郑晓耘, 李净凯, 张娜, 刘小丽, 刘远上. 基于大数据的烟草仓库温湿度智能调控系统设计[J]. 湖北农业科学, 2025, 64(5): 141-146.
[11]	仇艳平, 蔡柯, 霍光, 田馨誊, 马俊锋, 张自豪, 张佳轩, 邝雪灵, 胡佳丽, 郑玉欣, 王义伟, 曹媛媛. 根际解钾菌TK35促进烟草生长、钾素吸收及烟叶产质量提升[J]. 湖北农业科学, 2025, 64(4): 90-94.
[12]	张智丽, 张良凤, 刘毅, 李东梅, 王凯涛, 黄静, 郭靖. 烟草废弃物与生石灰复配对福寿螺的控制效果[J]. 湖北农业科学, 2025, 64(3): 79-85.
[13]	赵阿娟, 区禧贤, 翟争光, 周世民, 薄纯斌, 龙大彬, 李波, 阮彬洲, 段美珍. 一次性施用缓控释氮钾肥对烟草生长的影响[J]. 湖北农业科学, 2025, 64(11): 102-109.
[14]	李浩, 李传宗, 陈璇璇, 郑卜凡, 余君. 汉逊酵母增香介质制备条件优化对雪茄烟叶的影响[J]. 湖北农业科学, 2025, 64(11): 144-150.
[15]	彭宇, 李彩斌, 马黔, 唐艾, 顾姣, 彭铜, 王茂贤, 黄衍章, 李章海. 阿维菌素B₂和氟吡菌酰胺对根结线虫二龄幼虫的混合毒力及田间防治效果[J]. 湖北农业科学, 2025, 64(10): 94-98.