“赤霞珠”葡萄叶片缺磷胁迫的VIS/NIR光谱快速无损诊断方法

doi:10.3964/j.issn.1000-0593(2023)12-3719-07

摘要
参考文献
相关文章 (15)

全文: PDF (11155 KB)
输出: BibTeX | EndNote (RIS)

摘要：研究旨在明确“赤霞珠（Cabernet Sauvignon，Vitis Vinifera L.）”葡萄健康叶片和缺磷胁迫不同时期下的光谱信号特征变化，构建基于光谱技术的“赤霞珠”葡萄叶片缺磷胁迫快速无损诊断模型，为葡萄园病害防治与管理提供理论参考和技术支持。以酿酒葡萄“赤霞珠”葡萄叶片为研究对象，分别采集了正常、缺磷胁迫初期和末期葡萄叶的VIS/NIR反射率信息。对比Savitzky-Golay卷积平滑（S-G Smoothing）、移动平均平滑（MAS）、标准正态变换（SNV）和多元散射校正（MSC）4种预处理及组合方法对于去除葡萄叶光谱信号中随机噪声的能力，确定最佳预处理方法。采用连续投影法（SPA）筛选与“赤霞珠”葡萄叶缺磷胁迫相关的光谱特征变量，分别构建基于线性核函数（Linear）、多项式核函数（Poly）、径向基核函数（RBF）和二层神经网络核函数（Sigmoid）的支持向量机（SVM）模型，以灵敏度（SEN）和准确率（CCR）为依据评估模型诊断性能，形成基于VIS/NIR光谱的“赤霞珠”葡萄叶片缺磷胁迫快速无损诊断方法。S-G Smoothing预处理后的光谱信号的信噪比为110.58，以其为校正集构建的缺磷胁迫诊断模型最佳，因此确定其为最佳的预处理方法。采用主成分分析（PCA）计算样本光谱贡献率，以95%置信空间为依据检测数据集中的异常样本，最终发现并剔除了22的离群点。通过SPA筛选出402.6、404.6、409、411.5、539.4、691.9、729.9、838.7、1 011.9、1 017.5和1 020.5 nm等11个反映“赤霞珠”葡萄叶缺磷胁迫的光谱特征波段，作为缺磷胁迫快速无损诊断模型的输入变量。通过对比分析上述4种核函数SVM的诊断结果，以Linear为核函数构建的“赤霞珠”葡萄叶缺磷胁迫诊断模型能力最佳，对正常叶片诊断的SEN为81.08%，CCR为100%；对缺磷胁迫早期叶片诊断的SEN为100%，CCR为84.78%；对缺磷胁迫末期叶片诊断的SEN为100%，CCR为100%。该研究建立了基于VIS/NIR光谱的“赤霞珠”葡萄叶片缺磷胁迫快速无损诊断方法，能够满足葡萄园病害防治与智能化管理的生产需求，为酿酒葡萄智慧农业发展提供了技术参考。

关键词：酿酒葡萄；缺磷胁迫；可见光/近红外光谱；无损诊断；支持向量机

Abstract：The study aimed to clarify the VIS/NIR spectral characteristics of Cabernet Sauvignon leaves with phosphorus deficiency, then to construct a rapid and nondestructive diagnosis model, which is expected to help the vineyard management and disease control. Firstly, the grape leaves in healthy, early and later stress by phosphate deficiency were analyzed by VIS/NIR micro fiber spectrometer. In order to remove noise interference, four preprocessing methods, including Savitzky-Golay convolution smoothing (S-G Smoothing), moving average smoothing (MAS), standard normal variate (SNV) and multiple scattering corrections (MSC), were used to optimize spectral signals. Then, the successive projections algorithm (SPA) was used to select the feature wavebands of leaf phosphate deficiency. Finally, the support vector machine models were constructed based on four different kernel functions, including linear kernel function (Linear), polynomial kernel function (Poly), radial basis function (RBF) and Sigmoid tanh function (Sigmoid), to diagnose the phosphate deficiency of leaves. The sensitivity (SEN) and accuracy (CCR) were cited to assess the availability and effectiveness of those models. Experimental results proved that S-G Smoothing was the best preprocessing method because of the better signal-to-noise ratio of spectrum processed by it and the good availability of the model based on it. Principal component analysis (PCA) was used to find outliers with a confidence interval of 95%. 22 samples were identified with outliers and removed. Eleven wavebands (402.6, 404.6, 409.0, 411.5, 539.4, 691.9, 729.9, 838.7, 1 011.9, 1 017.5 and 1 020.5 nm) were selected by SPA to consider as reflecting the information of phosphate deficiency and be the input variables of the diagnosis model. After the contrast of four models with different kernel functions, it can be known that the SVM model with Linear showed better sensitivity and accuracy than others. Its SEN was 81.08%, and CCR was 100% for healthy leaves, its SEN was 100%, and CCR was 84.78% for early-stage diseased leaves, and its SEN and CCR were 100% for late-stage diseased leaves. In this study, A rapid and nondestructive diagnosis method was proposed based on VIS/NIR spectroscopy for phosphate deficiency of the Cabernet Sauvignon leaves, which is expected to improve the management and disease control of the vineyard and the intelligence of wine grape cultivation.

Key words：Enological grape; Phosphate deficiency; VIS/NIR spectroscopy; Nondestructive diagnosis; SVM

收稿日期: 2022-10-20 修订日期: 2023-05-17

中图分类号:

O433.4

基金资助: 国家自然科学基金青年科学基金项目（32202213），陕西省自然科学基金项目（2022JQ-222），新疆维吾尔自治区重点研发计划项目（2020B01005）资助

通讯作者: 陶永胜 E-mail: taoyongsheng@nwafu.edu.cn

作者简介: 白雪冰，1991年生，西北农林科技大学葡萄酒学院讲师 e-mail: bxb@nwafu.edu.cn

引用本文:

白雪冰，宋昌泽，张倩玮，代斌秀，靳国杰，刘文政，陶永胜. “赤霞珠”葡萄叶片缺磷胁迫的VIS/NIR光谱快速无损诊断方法[J]. 光谱学与光谱分析, 2023, 43(12): 3719-3725.
BAI Xue-bing, SONG Chang-ze, ZHANG Qian-wei, DAI Bin-xiu, JIN Guo-jie, LIU Wen-zheng, TAO Yong-sheng. Rapid and Nndestructive Dagnosis Mthod for Posphate Dficiency in “Cabernet Sauvignon” Gape Laves by Vis/NIR Sectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3719-3725.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2023)12-3719-07 或 https://www.gpxygpfx.com/CN/Y2023/V43/I12/3719

[1] BAI Xue-bing, YANG Jia-ning, JIANG Xing-rui, et al(白雪冰, 杨佳宁, 姜醒睿, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2022, 38(13): 319.
[2] Piccin R, Kaminski J, Ceretta C A, et al. Scientia Horticulturae, 2017, 218: 125.
[3] Tang Z, Yang J, Li Z, et al. Computers and Electronics in Agriculture, 2020, 178: 105735.
[4] Chen M, Brun F, Raynal M, et al. PLOS ONE, 2020, 15(3): e0230254.
[5] Shang L, Wan L, Zhou X, et al. PLOS ONE, 2020, 15(10): e0240559.
[6] Rasera J B, Amorim L, Marques J P R, et al. Physiological and Molecular Plant Pathology, 2019, 108: 101434.
[7] Rodriguez-Saona L, Aykas D P, Borba K R, et al. Current Opinion in Food Science, 2020, 31: 136.
[8] Mirzaei M, Verrelst J, Marofi S, et al. Remote sensing, 2019, 11(23): 2731.
[9] Roviello V, Caruso U, Dal Poggetto G, et al. Sustainability, 2021, 13(22): 12472.
[10] Pithan P A, Ducati J R, Garrido L R, et al. International Journal of Remote Sensing, 2021, 42(15): 5680.
[11] Junges A H, Almança M A K, Fajardo T V M, et al. Tropical Plant Pathology, 2020, 45: 522.
[12] Yang R, Lu X, Huang J, et al. Remote Sensing, 2021, 13(24): 5102.
[13] Rustioni L, Grossi D, Brancadoro L, et al. Plant Physiology and Biochemistry, 2017, 118: 342.
[14] Rustioni L, Grossi D, Brancadoro L, et al. Scientia Horticulturae, 2018, 241: 152.
[15] Cuq S, Lemetter V, Kleiber D, et al. International Journal of Environmental Analytical Chemistry, 2020, 100(10): 1179.
[16] Cuq S, Lemetter V, Kleiber D, et al. Computers and Electronics in Agriculture, 2020, 179: 105841.
[17] ZHANG Min, PAN Cun-de, LUO Wei(张敏, 潘存德, 罗威). Journal of Xinjiang Agricultural University(新疆农业大学学报), 2020, 43(4): 252.
[18] Li L, Wang S, Ren T, et al. Field Crops Research, 2018, 215: 173.
[19] Li H, Wei Z H, Wang X, et al. Journal of Applied Spectroscopy, 2020, 87: 553.
[20] Li W, Sun Z, Lu S, et al. Plant, Cell & Environment, 2019, 42(11): 3152.
[21] Jin J, Wang Q. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57(5): 3064.
[22] Hernández I, Gutiérrez S, Ceballos S, et al. Horticulturae, 2021, 7(5): 103.
[23] Lu W, Newlands N K, Carisse O, et al. Agronomy, 2020, 10(5): 622.