001046239 001__ 1046239
001046239 005__ 20250930132714.0
001046239 0247_ $$2doi$$a10.1016/j.atech.2025.101364
001046239 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-03759
001046239 0247_ $$2WOS$$aWOS:001568496000001
001046239 037__ $$aFZJ-2025-03759
001046239 041__ $$aEnglish
001046239 082__ $$a630
001046239 1001_ $$0P:(DE-Juel1)207602$$aAgarwal, Avinash$$b0$$eCorresponding author
001046239 245__ $$aSynergistic 3D, multispectral, and thermal image analysis via supervised machine learning for improved detection of root rot symptoms in hydroponically grown flat-leaf parsley
001046239 260__ $$bElsevier B.V.$$c2025
001046239 3367_ $$2DRIVER$$aarticle
001046239 3367_ $$2DataCite$$aOutput Types/Journal article
001046239 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1758894256_7208
001046239 3367_ $$2BibTeX$$aARTICLE
001046239 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001046239 3367_ $$00$$2EndNote$$aJournal Article
001046239 520__ $$aRoot rot in hydroponically grown leafy vegetables is difficult to detect via conventional manual and machine vision-based approaches as symptoms of infection are not clearly visible on the canopy at earlier stages of infection. Hence, the present study investigates the potential of using machine learning for assessing canopy information obtained from multiple imaging platforms synergistically to improve root rot detection. Herein, flat-leaf parsley seedlings were grown in an experimental hydroponic vertical farm and inoculated with Pythium irregulare and Phytophthora nicotianae. Subsequently, the seedlings were imaged via 3D, multispectral, and thermal sensors at various stages of growth to obtain twenty-six image-based plant features. Following a preliminary screening of redundant features via regression analysis, data for seventeen image features associated with morphometric, spectral, and thermal attributes was co-analyzed using supervised machine learning by Support Vector Machines (SVM). Models using all eleven spectral features provided 98 % accuracy compared to 90 % for all five morphometric features and 94 % for canopy temperature alone. Inclusion of temporal data improved model performance by ca. 0.5 %, 1.5 %, and 8 % for spectral, thermal, and morphometric datasets, respectively. Exhaustive feature selection using different SVM kernels and maximum feature thresholds showed that combining features across the three imaging platforms along with temporal information enabled better identification of infected samples (>99 %) with as low as three features in comparison to using considerably more features from individual imaging systems. Hence, fusion of data from multiple imaging systems and using it with temporal information enabled better real-time high-throughput monitoring of root rot.
001046239 536__ $$0G:(DE-HGF)POF4-2171$$a2171 - Biological and environmental resources for sustainable use (POF4-217)$$cPOF4-217$$fPOF IV$$x0
001046239 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001046239 7001_ $$0P:(DE-HGF)0$$ade Jesus Colwell, Filipe$$b1
001046239 7001_ $$0P:(DE-HGF)0$$aBello Rodriguez, Julian$$b2
001046239 7001_ $$0P:(DE-HGF)0$$aSommer, Sarah$$b3
001046239 7001_ $$0P:(DE-HGF)0$$aBarman, Monica$$b4
001046239 7001_ $$0P:(DE-HGF)0$$aCorrea Galvis, Viviana Andrea$$b5
001046239 7001_ $$0P:(DE-HGF)0$$aHill, Tom R.$$b6
001046239 7001_ $$0P:(DE-HGF)0$$aBoonham, Neil$$b7
001046239 7001_ $$0P:(DE-HGF)0$$aPrashar, Ankush$$b8
001046239 773__ $$0PERI:(DE-600)3094269-X$$a10.1016/j.atech.2025.101364$$gVol. 12, p. 101364 -$$p101364$$tSmart agricultural technology$$v12$$x2772-3755$$y2025
001046239 8564_ $$uhttps://juser.fz-juelich.de/record/1046239/files/1-s2.0-S2772375525005957-main.pdf$$yOpenAccess
001046239 909CO $$ooai:juser.fz-juelich.de:1046239$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001046239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)207602$$aForschungszentrum Jülich$$b0$$kFZJ
001046239 9131_ $$0G:(DE-HGF)POF4-217$$1G:(DE-HGF)POF4-210$$2G:(DE-HGF)POF4-200$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-2171$$aDE-HGF$$bForschungsbereich Erde und Umwelt$$lErde im Wandel – Unsere Zukunft nachhaltig gestalten$$vFür eine nachhaltige Bio-Ökonomie – von Ressourcen zu Produkten$$x0
001046239 9141_ $$y2025
001046239 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-17
001046239 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001046239 915__ $$0StatID:(DE-HGF)0112$$2StatID$$aWoS$$bEmerging Sources Citation Index$$d2024-12-17
001046239 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-10-22T13:01:47Z
001046239 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-10-22T13:01:47Z
001046239 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2024-12-17
001046239 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-17
001046239 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001046239 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2021-10-22T13:01:47Z
001046239 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2024-12-17
001046239 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-17
001046239 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-17
001046239 920__ $$lno
001046239 9201_ $$0I:(DE-Juel1)IBG-2-20101118$$kIBG-2$$lPflanzenwissenschaften$$x0
001046239 980__ $$ajournal
001046239 980__ $$aVDB
001046239 980__ $$aUNRESTRICTED
001046239 980__ $$aI:(DE-Juel1)IBG-2-20101118
001046239 9801_ $$aFullTexts