Near-infrared spectroscopy and deep neural networks for early common root rot detection in wheat from multi-season trials

IF 2 3区 农林科学 Q2 AGRONOMY Agronomy Journal Pub Date : 2024-07-30 DOI:10.1002/agj2.21648
Yiyi Xiong, Cheryl McCarthy, Jacob Humpal, Cassandra Percy
{"title":"Near-infrared spectroscopy and deep neural networks for early common root rot detection in wheat from multi-season trials","authors":"Yiyi Xiong,&nbsp;Cheryl McCarthy,&nbsp;Jacob Humpal,&nbsp;Cassandra Percy","doi":"10.1002/agj2.21648","DOIUrl":null,"url":null,"abstract":"<p>In Australia, the soil-borne disease common root rot (<i>Bipolaris sorokiniana</i>) (CRR) in wheat (<i>Triticum aestivum</i> L.) leads to substantial yield losses, yet has limited visible aboveground symptoms, making detection and identification labor intensive. Near-infrared (NIR) spectroscopy offers an early potential identification solution for CRR in wheat and has previously been reported with success for crop disease detection. This study investigated the ability of nondestructive NIR spectroscopy in combination with deep neural networks (DNN), logistic regression (LR), and principal component analysis combined with support vector machines (PCA-SVM) for early-stage CRR detection in wheat. NIR spectra of five different wheat varieties with varying resistance to CRR were collected in two seasons of glasshouse and three seasons of field trials using a portable spectrometer. Results demonstrated that DNN outperformed LR and PCA-SVM, achieving 66%–91% average classification accuracy in glasshouse trials and an average accuracy of 73% with up to 87% in field trials, effectively distinguishing inoculated and non-inoculated wheat plants from seedling to anthesis stages. Validation with a third season of field data achieved an average of 77% accuracy for the most susceptible variety during the stem elongation stage. NIR reflectance within 1600–1700 nm was identified as most important for estimating CRR presence, with initial detection occurring 35 days after sowing (DAS) in the glasshouse and 46 DAS in the field. In conclusion, a NIR spectrometer with a DNN model successfully performed disease classification, with the potential as a portable early disease detection tool to assist farm management decisions.</p>","PeriodicalId":7522,"journal":{"name":"Agronomy Journal","volume":"116 5","pages":"2370-2390"},"PeriodicalIF":2.0000,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/agj2.21648","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Agronomy Journal","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/agj2.21648","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 0

Abstract

In Australia, the soil-borne disease common root rot (Bipolaris sorokiniana) (CRR) in wheat (Triticum aestivum L.) leads to substantial yield losses, yet has limited visible aboveground symptoms, making detection and identification labor intensive. Near-infrared (NIR) spectroscopy offers an early potential identification solution for CRR in wheat and has previously been reported with success for crop disease detection. This study investigated the ability of nondestructive NIR spectroscopy in combination with deep neural networks (DNN), logistic regression (LR), and principal component analysis combined with support vector machines (PCA-SVM) for early-stage CRR detection in wheat. NIR spectra of five different wheat varieties with varying resistance to CRR were collected in two seasons of glasshouse and three seasons of field trials using a portable spectrometer. Results demonstrated that DNN outperformed LR and PCA-SVM, achieving 66%–91% average classification accuracy in glasshouse trials and an average accuracy of 73% with up to 87% in field trials, effectively distinguishing inoculated and non-inoculated wheat plants from seedling to anthesis stages. Validation with a third season of field data achieved an average of 77% accuracy for the most susceptible variety during the stem elongation stage. NIR reflectance within 1600–1700 nm was identified as most important for estimating CRR presence, with initial detection occurring 35 days after sowing (DAS) in the glasshouse and 46 DAS in the field. In conclusion, a NIR spectrometer with a DNN model successfully performed disease classification, with the potential as a portable early disease detection tool to assist farm management decisions.

Abstract Image

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
用近红外光谱仪和深度神经网络从多季试验中检测小麦早期常见根腐病
在澳大利亚,小麦(Triticum aestivum L.)的土传病害普通根腐病(Bipolaris sorokiniana)(CRR)导致大量减产,但其地上部可见症状有限,使得检测和识别工作十分繁重。近红外(NIR)光谱为小麦中的 CRR 提供了一种早期潜在的识别解决方案,此前已有成功检测作物病害的报道。本研究调查了无损近红外光谱与深度神经网络(DNN)、逻辑回归(LR)和主成分分析与支持向量机(PCA-SVM)相结合对小麦早期 CRR 检测的能力。在两季温室试验和三季田间试验中,使用便携式光谱仪采集了五个不同小麦品种的近红外光谱,这些品种对 CRR 的抗性各不相同。结果表明 DNN 的表现优于 LR 和 PCA-SVM,在温室试验中平均分类准确率为 66%-91% ,在田间试验中平均准确率为 73%,最高达 87%,能有效区分从幼苗到开花期的接种和未接种小麦植株。通过第三季的田间数据验证,在茎伸长阶段对最易感品种的平均准确率达到 77%。1600-1700 nm 波长范围内的近红外反射率被认为是估计 CRR 是否存在的最重要指标,在温室中,播种后 35 天(DAS)和在田间 46 天(DAS)即可首次检测到。总之,带有 DNN 模型的近红外光谱仪成功地进行了病害分类,有望作为一种便携式早期病害检测工具协助农场管理决策。
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
Agronomy Journal
Agronomy Journal 农林科学-农艺学
CiteScore
4.70
自引率
9.50%
发文量
265
审稿时长
4.8 months
期刊介绍: After critical review and approval by the editorial board, AJ publishes articles reporting research findings in soil–plant relationships; crop science; soil science; biometry; crop, soil, pasture, and range management; crop, forage, and pasture production and utilization; turfgrass; agroclimatology; agronomic models; integrated pest management; integrated agricultural systems; and various aspects of entomology, weed science, animal science, plant pathology, and agricultural economics as applied to production agriculture. Notes are published about apparatus, observations, and experimental techniques. Observations usually are limited to studies and reports of unrepeatable phenomena or other unique circumstances. Review and interpretation papers are also published, subject to standard review. Contributions to the Forum section deal with current agronomic issues and questions in brief, thought-provoking form. Such papers are reviewed by the editor in consultation with the editorial board.
期刊最新文献
Issue Information Weed management in organic dryland wheat production in the Pacific Northwest Soil health benefits of compost persist two decades after single application to winter wheat Deriving general principles of agroecosystem multifunctionality with the Diverse Rotations Improve Valuable Ecosystem Services (DRIVES) network Multiyear productivity and nitrate-nitrogen loss from corn and prairie bioenergy cropping systems
×
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