Feature Selection and Spectral Indices for Identifying Maize Stress Types.

IF 2.2 3区 化学 Q2 INSTRUMENTS & INSTRUMENTATION
Yanru Li, Keming Yang, Bing Wu
{"title":"Feature Selection and Spectral Indices for Identifying Maize Stress Types.","authors":"Yanru Li, Keming Yang, Bing Wu","doi":"10.1177/00037028241279328","DOIUrl":null,"url":null,"abstract":"<p><p>This study aims to identify different types of stress on maize leaves using feature selection and spectral index methods. Spectral data were collected from leaves under heavy metal, water, fertilizer stress, as well as under normal healthy conditions. Preprocessing steps such as continuum removal (CR), standard normal variable (SNV) transformation, multiple scattering correction (MSC), detrend correction (DT), and first-order derivative (FOD) were applied to the raw spectra. Various feature selection methods including ReliefF, chi-square test, recursive feature elimination (FRE), mutual information (MI), random forest (RF), and gradient boosting tree (GBT) were employed to determine the importance scores of different spectral bands, thus identifying sensitive spectral features capable of distinguishing various stress types. Spectral indices for stress type differentiation were constructed using label correlation method. Classification models were built using support vector machine (SVM), K-nearest neighbors (KNN), Gaussian naive Bayes (GNB), extreme gradient boosting (XGBoost), RF, and adaptive boosting (AdaBoost) algorithms. Results indicate that the characteristic spectral bands for differentiating stress types are primarily distributed around the red edge (near 700-800 nm) and water absorption valley (near 1900 nm). Spectral indices constructed using combinations of spectral bands around the near-infrared plateau absorption valley (near 1185 nm) and water absorption valley (near 1460 nm) effectively differentiate maize stress types. Among the modeling classification algorithms, RF and AdaBoost algorithms exhibited optimal performance, demonstrating high classification accuracy on both training and validation sets. These findings hold promise for providing new technical support for maize stress monitoring and diagnosis in agricultural production.</p>","PeriodicalId":8253,"journal":{"name":"Applied Spectroscopy","volume":" ","pages":"37028241279328"},"PeriodicalIF":2.2000,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Spectroscopy","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1177/00037028241279328","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}
引用次数: 0

Abstract

This study aims to identify different types of stress on maize leaves using feature selection and spectral index methods. Spectral data were collected from leaves under heavy metal, water, fertilizer stress, as well as under normal healthy conditions. Preprocessing steps such as continuum removal (CR), standard normal variable (SNV) transformation, multiple scattering correction (MSC), detrend correction (DT), and first-order derivative (FOD) were applied to the raw spectra. Various feature selection methods including ReliefF, chi-square test, recursive feature elimination (FRE), mutual information (MI), random forest (RF), and gradient boosting tree (GBT) were employed to determine the importance scores of different spectral bands, thus identifying sensitive spectral features capable of distinguishing various stress types. Spectral indices for stress type differentiation were constructed using label correlation method. Classification models were built using support vector machine (SVM), K-nearest neighbors (KNN), Gaussian naive Bayes (GNB), extreme gradient boosting (XGBoost), RF, and adaptive boosting (AdaBoost) algorithms. Results indicate that the characteristic spectral bands for differentiating stress types are primarily distributed around the red edge (near 700-800 nm) and water absorption valley (near 1900 nm). Spectral indices constructed using combinations of spectral bands around the near-infrared plateau absorption valley (near 1185 nm) and water absorption valley (near 1460 nm) effectively differentiate maize stress types. Among the modeling classification algorithms, RF and AdaBoost algorithms exhibited optimal performance, demonstrating high classification accuracy on both training and validation sets. These findings hold promise for providing new technical support for maize stress monitoring and diagnosis in agricultural production.

用于识别玉米胁迫类型的特征选择和光谱指数
本研究旨在利用特征选择和光谱指数方法识别玉米叶片上不同类型的胁迫。光谱数据采集自重金属、水和肥料胁迫以及正常健康条件下的叶片。对原始光谱进行了预处理,如连续体去除(CR)、标准正态变量(SNV)变换、多重散射校正(MSC)、去趋势校正(DT)和一阶导数(FOD)。采用各种特征选择方法,包括ReliefF、卡方检验、递归特征消除(FRE)、互信息(MI)、随机森林(RF)和梯度提升树(GBT)来确定不同波段的重要性得分,从而识别出能够区分各种应力类型的敏感光谱特征。利用标签相关法构建了用于区分应力类型的光谱指数。使用支持向量机 (SVM)、K-近邻 (KNN)、高斯天真贝叶斯 (GNB)、极梯度提升 (XGBoost)、RF 和自适应提升 (AdaBoost) 算法建立了分类模型。结果表明,用于区分应力类型的特征光谱带主要分布在红色边缘(700-800 nm 附近)和吸水谷(1900 nm 附近)。利用近红外高原吸收谷(1185 nm 附近)和水分吸收谷(1460 nm 附近)附近的光谱带组合构建的光谱指数可有效区分玉米胁迫类型。在建模分类算法中,RF 算法和 AdaBoost 算法表现出最佳性能,在训练集和验证集上都表现出较高的分类准确性。这些发现有望为农业生产中的玉米胁迫监测和诊断提供新的技术支持。
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 求助全文
来源期刊
Applied Spectroscopy
Applied Spectroscopy 工程技术-光谱学
CiteScore
6.60
自引率
5.70%
发文量
139
审稿时长
3.5 months
期刊介绍: Applied Spectroscopy is one of the world''s leading spectroscopy journals, publishing high-quality peer-reviewed articles, both fundamental and applied, covering all aspects of spectroscopy. Established in 1951, the journal is owned by the Society for Applied Spectroscopy and is published monthly. The journal is dedicated to fulfilling the mission of the Society to “…advance and disseminate knowledge and information concerning the art and science of spectroscopy and other allied sciences.”
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信