Prediction of secondary metabolites in maize under different nitrogen inputs by hyperspectral sensing and machine learning

IF 3.1 3区 物理与天体物理 Q2 INSTRUMENTS & INSTRUMENTATION Infrared Physics & Technology Pub Date : 2024-08-25 DOI:10.1016/j.infrared.2024.105524
Meessias Antônio da Silva , Cid Naudi Silva Campos , Renato de Mello Prado , Alessandra Rodrigues dos Santos , Ana Carina da Silva Candido , Dthenifer Cordeiro Santana , Izabela Cristina de Oliveira , Fábio Henrique Rojo Baio , Carlos Antonio da Silva Junior , Larissa Pereira Ribeiro Teodoro , Paulo Eduardo Teodoro
{"title":"Prediction of secondary metabolites in maize under different nitrogen inputs by hyperspectral sensing and machine learning","authors":"Meessias Antônio da Silva ,&nbsp;Cid Naudi Silva Campos ,&nbsp;Renato de Mello Prado ,&nbsp;Alessandra Rodrigues dos Santos ,&nbsp;Ana Carina da Silva Candido ,&nbsp;Dthenifer Cordeiro Santana ,&nbsp;Izabela Cristina de Oliveira ,&nbsp;Fábio Henrique Rojo Baio ,&nbsp;Carlos Antonio da Silva Junior ,&nbsp;Larissa Pereira Ribeiro Teodoro ,&nbsp;Paulo Eduardo Teodoro","doi":"10.1016/j.infrared.2024.105524","DOIUrl":null,"url":null,"abstract":"<div><p>Flavonoids are compounds resulting from secondary plant metabolism that provide benefits to human health by food. This study aimed to accuracy of predicting flavonoids in maize plants subjected to different nitrogen rates using hyperspectral reflectance and machine learning (ML) algorithms. The experiment was carried out in randomized blocks in a 4 × 5 factorial design (four N inputs: 0; 30; 60 and 120 % of the recommended N input; and five readings of the reflectance spectra in maize leaves from different vegetative stages: V6, V8, V10, V12 and V14, in four replications, totaling 80 treatments. N rates were applied in the V4 and V8 phenological stages, using urea as the N source. For hyperspectral analysis, four leaves from each treatment were collected and analyzed using a spectroradiometer (FieldSpec 4 HRes, Analytical Spectral Devices), capturing the spectrum in the 350 to 2500 nm range. Subsequently, the leaf samples used in the reflectance readings were dried, ground and subjected to isoflavone quantification, analyzed by ultra-performance liquid chromatography in three repetitions, quantifying daidzein 1 (D1), daidzein 2 (D2), genistein 1 (G1), genistein 2 (G2), and total isoflavones. Data obtained was subjected to machine learning analysis, testing two data set input configurations: wavelengths (WL) and calculated spectral bands (B), and D1, D2, G1, G2 and total isoflavones as output variables. The ML algorithms tested were artificial neural networks (ANN), REPTree (DT), M5P decision tree (M5P), ZeroR (R), Random Forest (RF) and support vector machine (SVM), evaluated according to their performance by the correlation coefficient (r) and mean absolute error (MAE). The results show that the SVM algorithm had the highest accuracy in predicting the variables D1, D2, G1, G2 and total isoflavones, outperforming the other algorithms when WL was used as input in dataset.</p></div>","PeriodicalId":13549,"journal":{"name":"Infrared Physics & Technology","volume":"142 ","pages":"Article 105524"},"PeriodicalIF":3.1000,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Infrared Physics & Technology","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1350449524004080","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}
引用次数: 0

Abstract

Flavonoids are compounds resulting from secondary plant metabolism that provide benefits to human health by food. This study aimed to accuracy of predicting flavonoids in maize plants subjected to different nitrogen rates using hyperspectral reflectance and machine learning (ML) algorithms. The experiment was carried out in randomized blocks in a 4 × 5 factorial design (four N inputs: 0; 30; 60 and 120 % of the recommended N input; and five readings of the reflectance spectra in maize leaves from different vegetative stages: V6, V8, V10, V12 and V14, in four replications, totaling 80 treatments. N rates were applied in the V4 and V8 phenological stages, using urea as the N source. For hyperspectral analysis, four leaves from each treatment were collected and analyzed using a spectroradiometer (FieldSpec 4 HRes, Analytical Spectral Devices), capturing the spectrum in the 350 to 2500 nm range. Subsequently, the leaf samples used in the reflectance readings were dried, ground and subjected to isoflavone quantification, analyzed by ultra-performance liquid chromatography in three repetitions, quantifying daidzein 1 (D1), daidzein 2 (D2), genistein 1 (G1), genistein 2 (G2), and total isoflavones. Data obtained was subjected to machine learning analysis, testing two data set input configurations: wavelengths (WL) and calculated spectral bands (B), and D1, D2, G1, G2 and total isoflavones as output variables. The ML algorithms tested were artificial neural networks (ANN), REPTree (DT), M5P decision tree (M5P), ZeroR (R), Random Forest (RF) and support vector machine (SVM), evaluated according to their performance by the correlation coefficient (r) and mean absolute error (MAE). The results show that the SVM algorithm had the highest accuracy in predicting the variables D1, D2, G1, G2 and total isoflavones, outperforming the other algorithms when WL was used as input in dataset.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用高光谱传感和机器学习预测不同氮输入条件下玉米的次生代谢产物
类黄酮是植物二次新陈代谢产生的化合物,通过食用对人体健康有益。本研究旨在利用高光谱反射率和机器学习(ML)算法,准确预测不同氮含量条件下玉米植株的类黄酮含量。实验采用 4 × 5 因式设计的随机区组进行(四种氮投入量:0;30;60 和 120 %):四种氮投入量:推荐氮投入量的 0%、30%、60% 和 120%;五次读取不同植株阶段玉米叶片的反射光谱:四个重复共 80 个处理。在 V4 和 V8 物候期使用尿素作为氮源。为了进行高光谱分析,每个处理收集四片叶子,并使用光谱辐射计(FieldSpec 4 HRes,Analytical Spectral Devices)进行分析,捕捉 350 至 2500 nm 范围内的光谱。随后,将用于读取反射率的叶片样本烘干、研磨并进行异黄酮定量,采用超高效液相色谱法进行分析,共重复三次,分别定量分析了大地雌酚 1 (D1)、大地雌酚 2 (D2)、染料木素 1 (G1)、染料木素 2 (G2) 和总异黄酮。获得的数据进行了机器学习分析,测试了两个数据集输入配置:波长(WL)和计算光谱带(B),以及作为输出变量的 D1、D2、G1、G2 和总异黄酮。测试的 ML 算法包括人工神经网络 (ANN)、REPTree (DT)、M5P 决策树 (M5P)、ZeroR (R)、随机森林 (RF) 和支持向量机 (SVM),根据相关系数 (r) 和平均绝对误差 (MAE) 评估其性能。结果表明,当数据集输入 WL 时,SVM 算法预测变量 D1、D2、G1、G2 和总异黄酮的准确率最高,优于其他算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
5.70
自引率
12.10%
发文量
400
审稿时长
67 days
期刊介绍: The Journal covers the entire field of infrared physics and technology: theory, experiment, application, devices and instrumentation. Infrared'' is defined as covering the near, mid and far infrared (terahertz) regions from 0.75um (750nm) to 1mm (300GHz.) Submissions in the 300GHz to 100GHz region may be accepted at the editors discretion if their content is relevant to shorter wavelengths. Submissions must be primarily concerned with and directly relevant to this spectral region. Its core topics can be summarized as the generation, propagation and detection, of infrared radiation; the associated optics, materials and devices; and its use in all fields of science, industry, engineering and medicine. Infrared techniques occur in many different fields, notably spectroscopy and interferometry; material characterization and processing; atmospheric physics, astronomy and space research. Scientific aspects include lasers, quantum optics, quantum electronics, image processing and semiconductor physics. Some important applications are medical diagnostics and treatment, industrial inspection and environmental monitoring.
期刊最新文献
Breaking dimensional barriers in hyperspectral target detection: Atrous convolution with Gramian Angular field representations Multi-Scale convolutional neural network for finger vein recognition Temporal denoising and deep feature learning for enhanced defect detection in thermography using stacked denoising convolution autoencoder Detection of black tea fermentation quality based on optimized deep neural network and hyperspectral imaging Hyperspectral and multispectral images fusion based on pyramid swin transformer
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1