Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning

Cassava brown streak disease (CBSD) is an emerging viral disease that can greatly reduce cassava productivity, while causing only mild aerial symptoms that develop late in infection. Early detection of CBSD enables better crop management and intervention. Current techniques require laboratory equipm...

Descripción completa

Detalles Bibliográficos
Autores principales: Peng, Y., Dallas, M.M., Ascencio‑Ibanez, J.T., Hoyer, J.S., Legg, James P., Hanley-Bowdoin, L., Grieve, B., Yin, H.
Formato: Journal Article
Lenguaje:Inglés
Publicado: Springer 2022
Materias:
Acceso en línea:https://hdl.handle.net/10568/125990
_version_ 1855523582898077696
author Peng, Y.
Dallas, M.M.
Ascencio‑Ibanez, J.T.
Hoyer, J.S.
Legg, James P.
Hanley-Bowdoin, L.
Grieve, B.
Yin, H.
author_browse Ascencio‑Ibanez, J.T.
Dallas, M.M.
Grieve, B.
Hanley-Bowdoin, L.
Hoyer, J.S.
Legg, James P.
Peng, Y.
Yin, H.
author_facet Peng, Y.
Dallas, M.M.
Ascencio‑Ibanez, J.T.
Hoyer, J.S.
Legg, James P.
Hanley-Bowdoin, L.
Grieve, B.
Yin, H.
author_sort Peng, Y.
collection Repository of Agricultural Research Outputs (CGSpace)
description Cassava brown streak disease (CBSD) is an emerging viral disease that can greatly reduce cassava productivity, while causing only mild aerial symptoms that develop late in infection. Early detection of CBSD enables better crop management and intervention. Current techniques require laboratory equipment and are labour intensive and often inaccurate. We have developed a handheld active multispectral imaging (A-MSI) device combined with machine learning for early detection of CBSD in real-time. The principal benefits of A-MSI over passive MSI and conventional camera systems are improved spectral signal-to-noise ratio and temporal repeatability. Information fusion techniques further combine spectral and spatial information to reliably identify features that distinguish healthy cassava from plants with CBSD as early as 28 days post inoculation on a susceptible and a tolerant cultivar. Application of the device has the potential to increase farmers’ access to healthy planting materials and reduce losses due to CBSD in Africa. It can also be adapted for sensing other biotic and abiotic stresses in real-world situations where plants are exposed to multiple pest, pathogen and environmental stresses.
format Journal Article
id CGSpace125990
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Springer
publisherStr Springer
record_format dspace
spelling CGSpace1259902025-11-11T10:14:52Z Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning Peng, Y. Dallas, M.M. Ascencio‑Ibanez, J.T. Hoyer, J.S. Legg, James P. Hanley-Bowdoin, L. Grieve, B. Yin, H. plant viruses machine learning cassava productivity Cassava brown streak disease (CBSD) is an emerging viral disease that can greatly reduce cassava productivity, while causing only mild aerial symptoms that develop late in infection. Early detection of CBSD enables better crop management and intervention. Current techniques require laboratory equipment and are labour intensive and often inaccurate. We have developed a handheld active multispectral imaging (A-MSI) device combined with machine learning for early detection of CBSD in real-time. The principal benefits of A-MSI over passive MSI and conventional camera systems are improved spectral signal-to-noise ratio and temporal repeatability. Information fusion techniques further combine spectral and spatial information to reliably identify features that distinguish healthy cassava from plants with CBSD as early as 28 days post inoculation on a susceptible and a tolerant cultivar. Application of the device has the potential to increase farmers’ access to healthy planting materials and reduce losses due to CBSD in Africa. It can also be adapted for sensing other biotic and abiotic stresses in real-world situations where plants are exposed to multiple pest, pathogen and environmental stresses. 2022-02-24 2022-12-14T12:47:28Z 2022-12-14T12:47:28Z Journal Article https://hdl.handle.net/10568/125990 en Open Access application/pdf Springer Peng, Y., Dallas, M.M., Ascencio-Ibáñez, J.T., Hoyer, J.S., Legg, J., Hanley-Bowdoin, L., ... & Yin, H. (2022). Early detection of plant virus infection using multispectral imaging and spatial–spectral machine learning. Scientific Reports, 12(1): 3113, 1-14.
spellingShingle plant viruses
machine learning
cassava
productivity
Peng, Y.
Dallas, M.M.
Ascencio‑Ibanez, J.T.
Hoyer, J.S.
Legg, James P.
Hanley-Bowdoin, L.
Grieve, B.
Yin, H.
Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning
title Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning
title_full Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning
title_fullStr Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning
title_full_unstemmed Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning
title_short Early detection of plant virus infection using multispectral imaging and spatial-spectral machine learning
title_sort early detection of plant virus infection using multispectral imaging and spatial spectral machine learning
topic plant viruses
machine learning
cassava
productivity
url https://hdl.handle.net/10568/125990
work_keys_str_mv AT pengy earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning
AT dallasmm earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning
AT ascencioibanezjt earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning
AT hoyerjs earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning
AT leggjamesp earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning
AT hanleybowdoinl earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning
AT grieveb earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning
AT yinh earlydetectionofplantvirusinfectionusingmultispectralimagingandspatialspectralmachinelearning