花叶病胁迫下甘蔗叶片叶绿素含量的高光谱预测模型

doi:10.3964/j.issn.1000-0593(2023)09-2885-09

摘要
参考文献
相关文章 (6)

全文: PDF (11022 KB)
输出: BibTeX | EndNote (RIS)

摘要：叶绿素含量是甘蔗在生长监测中非常重要的评估内容，尤其是在甘蔗受到病害侵染的情况下，准确估计叶绿素含量有利于病害的早期检测与防治，在实际生产中具有重要意义。为了构建花叶病胁迫下甘蔗叶片叶绿素含量估计模型，于2021年7月到11月通过人工接种病菌，使甘蔗叶片感染花叶病。对这些感染了花叶病的叶片重复测量高光谱数据。并通过化学方法测量叶片的叶绿素含量，以此建立花叶病胁迫下的甘蔗叶片高光谱数据集。首先使用Savitzky-Golay卷积平滑（SG）、多元散射校正（MSC）、变量标准化（SNV）、一阶导数（1^st D）、二阶导数（2^nd D）5种高光谱数据预处理方法建立偏最小二乘回归（PLSR）检测模型，从而构建高光谱数据最优预处理模型。利用最优预处理结果，分别采用相关系数、连续投影算法（SPA）和随机森林算法（RF）筛选特征波段。将筛选出的波段分别和BP神经网络（BPNN）、支持向量回归（SVR）、K最邻近法（KNN）等机器学习模型结合建立叶绿素含量预测模型。结果表明，基于SG处理后建立的PLSR模型精度最高R²_p=0.9952，RMSE_p=0.235 3 mg·cm^-2。用RF筛选出的特征波段与BPNN学习模型结合的SG-RF-BPNN模型为花叶病胁迫下甘蔗叶片叶绿素含量的最优预测模型，R²_p=0.996 4，RMSE_p=0.205 8 mg·cm^-2。提出的基于高光谱信息的花叶病胁迫下的叶绿素含量预测模型具有较高的精度和预测能力，可为大面积种植的甘蔗精准、无损伤的病害胁迫检测提供科学依据。

关键词：甘蔗；花叶病胁迫；叶绿素含量预测；高光谱分析；特征波段提取

Abstract：Chlorophyll is a critical evaluation content of sugarcane growth monitoring, especially when diseases infected sugarcane. Accurate estimation of chlorophyll content is beneficial for the early detection and control of diseases, which is of great importance in practical production. In order to determine the best prediction model of chlorophyll content in sugarcane leaves, this study infected sugarcane leaves with mosaic from July to November, 2021 through artificial inoculation of pathogenic bacteria. Among them were 35 infected plants and 35 healthy plants, and two leaves were collected for each pot. Repeat the measurement of the leaf hyperspectral data using the spectrometer. The chlorophyll content of chemical leaves was measured to establish a hyperspectral data set of sugarcane leaves. In this study, five pre-processing methods, SG, MSC, SNV, 1^st D and 2^nd D, were used to establish the PLSR detection model and determine the best preprocessing method. Based on the optimized pretreatment results, correlation coefficient, SPA and RF were used to select the characteristic bands of chlorophyll content in sugarcane leaves, and the selected bands were combined with BPNN, SVR and KNN to establish chlorophyll prediction models. The results showed that the PLSR model based on SG treatment has the highest accuracy R²_p=0.995 2, and the RMSE_p=0.235 3 mg·cm^-2. The model combined with the BPNN algorithm using RF screening was the optimal prediction model of chlorophyll content in sugarcane leaves under mosaic disease stress, the decision coefficient of the SG-RF-BPNN model was R²_p=0.996 4, and the RMSE_p=0.205 8 mg·cm^-2, which had high accuracy and predictive power. It will provide a theoretical basis for the accurate and injury-free disease stress detection of large-scale sugarcane.

Key words：Sugarcane; Mosaic disease: Chlorophyll content: Hyperspectral: Machine learning

收稿日期: 2022-05-03 修订日期: 2022-08-12

中图分类号:

S566.1

基金资助: 国家自然科学基金青年科学基金项目（31901466）资助

通讯作者: 盖倞尧，王梓廷 E-mail: jygai@gxu.edu.cn；zitingwang@gxu.edu.cn

作者简介: 王敬湧，1997年生，广西大学机械工程学院硕士研究生 e-mail: 2011391091@st.gxu.edu.cn
谢洒洒，女，1994年生，广西大学农学院硕士研究生 e-mail: 1917391027@st.gxu.edu.cn
王敬湧，谢洒洒：并列第一作者

引用本文:

王敬湧，谢洒洒，盖倞尧，王梓廷. 花叶病胁迫下甘蔗叶片叶绿素含量的高光谱预测模型[J]. 光谱学与光谱分析, 2023, 43(09): 2885-2893.
WANG Jing-yong, XIE Sa-sa, GAI Jing-yao, WANG Zi-ting. Hyperspectral Prediction Model of Chlorophyll Content in Sugarcane Leaves Under Stress of Mosaic. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2885-2893.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2023)09-2885-09 或 https://www.gpxygpfx.com/CN/Y2023/V43/I09/2885

[1] Aguiar N O, Medici L O, Olivares F L, et al. Annals of Applied Biology, 2016, 168(2): 203.
[2] Lipps P E. Mycologia, 1990, 82(5): 663.
[3] YUE Xue-jun, QUAN Dong-ping, HONG Tian-sheng, et al(岳学军, 全东平, 洪添胜, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2015, 31(1): 294.
[4] Yamashita H, Sonobe R, Hirono Y, et al. Scientific Reports, 2020, 10(1): 17360.
[5] SUN Hong, ZHENG Tao, LIU Ning, et al(孙红, 郑涛, 刘宁, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2018, 34(1): 149.
[6] DONG Zhe, YANG Wu-de, ZHU Hong-fen, et al(董哲, 杨武德, 朱洪芬, 等). Journal of Shangxi Agricultural Sciences(山西农业科学), 2019, 47(5): 751.
[7] An G, Xing M, He B, et al. Remote Sensing, 2020, 12(18): 3104.
[8] Bhadra S, Sagan V, Maimaitijiang M, et al. Remote Sensing, 2020, 12(13): 2082.
[9] LI Chang-chun, SHI Jin-Jin, MA Chun-yan, et al(李长春, 施锦锦, 马春艳, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2021, 52(8): 172.
[10] TANG Yan-lin, WANG Ren-chao, WANG Xiu-zhen, et al(唐延林, 王人潮, 王秀珍, 等). Journal of Sounth China Agricultural University(华南农业大学学报), 2003, 24(1): 4.
[11] Baffi G, Martin E B, Morris A J. Computers and Chemical Engineering, 1999, 23(9): 1293.
[12] Khoshhal J, Mokarram M. International Journal of Environmental Sciences, 2012, 3(3): 1000.
[13] Cover T M, Hart P E. IEEE Transactions on Information Theory, 1967, 13(1): 21.
[14] Fan J, Yue W, Wu L, et al. Agricultural and Forest Meteorology, 2018, 263: 225.
[15] WANG Hai-long, YANG Guo-guo, ZHANG Yu, et al(王海龙, 杨国国, 张瑜, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(7): 2115.
[16] Araújo M C U, Saldanha T C B, Galvão R K H, et al. Chemometrics and Intelligent Laboratory Systems, 2001, 57(2): 65.
[17] Bylander T. Machine Learning, 2002, 48(1-3): 287.