基于多光谱和高光谱的茶树越冬期REC、SPAD和MDA预测模型

doi:10.3964/j.issn.1000-0593(2025)01-0256-08

摘要
参考文献
相关文章 (15)

全文: PDF (14071 KB)
输出: BibTeX | EndNote (RIS)

摘要：抗寒生理指标的测定是评价茶树抗寒性的重要途径。传统上，茶树抗寒性的评价方法主要是通过测定茶树在低温胁迫下的理化参数。然而，这些方法不仅费时费力，而且具有破坏性。该研究建立了一种基于多光谱和高光谱成像技术的茶树抗寒性REC、SPAD、MDA预测模型。首先，采集了低温胁迫下32份育种材料的多光谱与高光谱图像，并测定相应茶树叶片的REC、SPAD、MDA、SP和SS含量。其次，对其中的高光谱图像数据采用MSC、SNV、S-G、1-D和2-D五种方法进行光谱预处理，采用UVE和SPA两种方法筛选特征波段。最后，分别对多光谱和高光谱数据采用SVM、RF和PLS算法建立茶树抗寒性REC、SPAD、MDA预测模型。结果表明，（1）MSC、SNV、S-G、1-D和2-D联合预处理后的光谱更加稳定，峰谷更加突出，模型的准确性和可靠性更高；（2）UVE算法筛选的特征波段数量最多，而SPA算法筛选的特征波段数量最少，更适合高光谱数据建立回归模型；（3）RF模型在多光谱成像预测叶片的REC（R_p=0.735 2，RMSEP=0.077 1）、SPAD（R_p=0.502 9，RMSEP=6.681 8）和MDA含量（R_p=0.784 6，RMSEP=8.885 3）方面具有最高的精度；SPA-SVM模型在高光谱成像预测叶片的SPAD（R_p=0.734 9，RMSEP=4.154 6）和MDA（R_p=0.685 8，RMSEP=8.548 8）方面具有最高的精度，SPA-PLS模型在预测REC（R_p=0.629 8，RMSEP=0.066 9）方面具有最高的精度。因此，基于多光谱、高光谱成像和机器学习算法的REC、SPAD、MDA预测模型提供了一种准确、无损和高效的方法，对茶树抗寒性评价具有重要意义。

关键词：茶树；多光谱成像；高光谱成像；机器学习；无损检测；抗寒性

Abstract：Determining cold resistance physiological indicators is an important way to evaluate the cold resistance of tea plants. Traditionally, methods of evaluating the cold tolerance of tea trees are mainly through the determination of physicochemical parameters of tea trees under low-temperature stress. However, these methods are not only time-consuming and labor-intensive but also destructive. This study established a prediction model for REC, SPAD, and MDA of tea tree cold resistance based on multispectral and hyperspectral imaging techniques. Firstly, multispectral and hyperspectral images of 32 breeding materials under low-temperature stress were collected, and the REC, SPAD, MDA, SP, and SS contents of the corresponding tea tree leaves were determined. Secondly, the hyperspectral image data among them were spectrally pre-processed using five methods, namely, MSC, SNV, S-G, 1-D, and 2-D, and the characteristic bands were screened using two methods, UVE and SPA. Finally, the REC, SPAD, and MDA prediction models of tea tree cold resistance were established using SVM, RF, and PLS algorithms for multispectral and hyperspectral data. The results showed that (1) the spectral curves were more stable, the peaks and valleys were more prominent, and the accuracy and reliability of the models were higher after the joint preprocessing of MSC, SNV, S-G, 1-D and 2-D; (2) the UVE algorithm screened the largest number of characteristic bands, while the SPA algorithm screened the smallest number of characteristic bands, which was more suitable for establishing regression models with hyperspectral data; (3) The RF model has the highest accuracy in predicting leaf REC (R_p=0.735 2，RMSEP=0.077 1), SPAD (R_p=0.502 9，RMSEP=6.681 8), and MDA (R_p=0.784 6，RMSEP=8.885 3) content under multispectral imaging techniques; the SPA-SVM model has the highest accuracy in predicting leaf SPAD (R_p=0.734 9，RMSEP=4.154 6) and MDA (R_p=0.685 8，RMSEP=8.548 8) under hyperspectral imaging techniques, and the SPA-PLS model has the highest accuracy in predicting REC (R_p=0.629 8，RMSEP=0.066 9). Therefore, the REC, SPAD, and MDA prediction models based on multispectral and hyperspectral imaging and machine learning algorithms provide an accurate, non-destructive, and efficient method, which is of great significance for evaluating tea tree cold resistance.

Key words：Tea plant; Multispectral imaging; Hyperspectral imaging; Machine learning; Non-destructive testing; Cold tolerance

收稿日期: 2024-03-27 修订日期: 2024-08-15

中图分类号:

TP391.4

基金资助: 国家自然科学基金项目（32272767），山东省农业良种工程项目（2020LZGC010），科技型中小企业创新能力提升工程项目（2022TSGC2232），青岛市科技惠民示范专项项目（22-3-7-xdny-5-nsh）资助

通讯作者: 丁兆堂，范凯 E-mail: dzttea@163.com；fankaitea@163.com

作者简介: 徐阳，1999年生，青岛农业大学茶叶研究所硕士研究生 e-mail: xuyangtea99@163.com

引用本文:

徐阳，毛艺霖，李赫，王玉，王双双，钱文俊，丁兆堂，范凯. 基于多光谱和高光谱的茶树越冬期REC、SPAD和MDA预测模型[J]. 光谱学与光谱分析, 2025, 45(01): 256-263.
XU Yang, MAO Yi-lin, LI He, WANG Yu, WANG Shuang-shuang, QIAN Wen-jun, DING Zhao-tang, FAN Kai. Multispectral and Hyperspectral Prediction Models of REC, SPAD and MDA in Overwintered Tea Plant. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(01): 256-263.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2025)01-0256-08 或 https://www.gpxygpfx.com/CN/Y2025/V45/I01/256

[1] Yang Yazhuo, Li Tong, Teng Ruimin, et al. Scientia Horticulturae, 2021, 285: 110164.
[2] Ali M M, Bachik N A, Muhadi N A, et al. Physiological and Molecular Plant Pathology, 2019, 108: 101426.
[3] Oerke E C, Herzog K, Toepfer R, et al. Journal of Experimental Botany, 2016, 67(18): 5529.
[4] Xu Yang, Mao Yilin, Li He, et al. Plant Methods, 2023, 19(1): 98.
[5] Feng Lei, Wu Baohua, He Yong, et al. Frontiers in Plant Science, 2021, 12: 693521.
[6] Luo Danni, Gao Yuan, Wang Yu, et al. Journal of the Science of Food and Agriculture, 2022, 102(4): 1540.
[7] Shi Yujie, Gao Yuan, Wang Yu, et al. Frontiers in Plant Science, 2022, 13: 820585.
[8] Chen Sizhou, Shen Jiazhi, Fan Kai, et al. Frontiers in Plant Science, 2022, 13: 1048442.
[9] de Oliveira Dias F, Magalhaes Valente D S, Oliveira C T, et al. International Journal of Remote Sensing, 2023, 44(6): 1900.
[10] MAO Yi-lin, LI He, WANG Yu, et al(毛艺霖，李赫，王玉，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(7): 2266.
[11] Li He, Mao Yilin, Shi Hongtao, et al. Scientia Horticulturae, 2024, 331: 113106.
[12] ZHANG Ling-zhi，HUANG Yan，YU Ying-jie, et al(张灵枝，黄艳，于英杰，等). Journal of Food Science and Biotechnology(食品与生物技术学报), 2024, 43(1): 48.
[13] Zhang Sulan, Huang Hong, Huang Yunbiao, et al. Applied Sciences, 2022, 12(13): 6676.
[14] Mao Yilin, Li He, Xu Yang, et al. Computers and Electronics in Agriculture, 2023, 213: 108176.
[15] Aptula A O, Jeliazkova N G, Schultz T W, et al. QSAR & Combinatorial Science, 2005, 24(3): 385.
[16] Wu Di, Nie Pengcheng, He Yong, et al. Food Bioprocess Technology, 2012, 5: 1402.
[17] Xu Shengxiang, Zhao Yongcun, Wang Meiyan, et al. Catena, 2017, 157: 12.
[18] Mao Yilin, Li He, Wang Yu, et al. Foods, 2022, 11(16): 2537.
[19] Chen Sizhou, Gao Yuan, Fan Kai, et al. Frontiers in Plant Science, 2021, 12: 695102.
[20] Mao Yilin, Li He, Wang Yu, et al. Frontiers in Plant Science, 2023, 14: 1096490.