Detection of biotic and abiotic stresses in crops by using hierarchical self organizing classifiers

A - Papers appearing in refereed journals

Pantazi, X., Dimitrios, M., Oberti, R., West, J. S., Mouazen, A. and Bochtis, D. 2017. Detection of biotic and abiotic stresses in crops by using hierarchical self organizing classifiers. Precision Agriculture. 18 (3), p. 383–393. https://doi.org/10.1007/s11119-017-9507-8

AuthorsPantazi, X., Dimitrios, M., Oberti, R., West, J. S., Mouazen, A. and Bochtis, D.
Abstract

Hyperspectral signatures can provide abundant information regarding health status of crops; however it is difficult to discriminate between biotic and abiotic stress. In this study, the case of simultaneous occurrence of yellow rust disease symptoms and nitrogen stress was investigated by using hyperspectral features from a ground based hyperspectral imaging system. Hyperspectral images of healthy and diseased plant canopies were taken at Rothamsted Research, UK by a Specim V10 spectrograph. Five wavebands of 20 nm width were utilized for accurate identification of each of the stress and healthy plant conditions. The technique that was developed used a hybrid classification scheme consisting of hierarchical self organizing classifiers. Three different architectures were considered: counter-propagation artificial neural networks, supervised Kohonen networks (SKNs) and XY-fusion. A total of 12 120 spectra were collected. From these 3 062 (25.3%) were used for testing. The results of biotic and abiotic stress identification appear to be promising, reaching more than 95% for all three architectures. The proposed approach aimed at sensor based detection of diseased and stressed plants so that can be treated site specifically contributing to a more effective and precise application of fertilizers and fungicides according to specific plant’s needs.

Keywordscrop disease; machine learning; neural networks; nitrogen stress; hyperspectral sensing
Year of Publication2017
JournalPrecision Agriculture
Journal citation18 (3), p. 383–393
Digital Object Identifier (DOI)https://doi.org/10.1007/s11119-017-9507-8
Open accessPublished as non-open access
FunderEuropean Union
Biotechnology and Biological Sciences Research Council
Funder project or codeEU QLK5-CT-1999-01280
Agrivision: Development of a system for low cost remotely managed, automated crop stress monitoring and detection
OPTIDIS project 2000-2004
BBSRC Strategic Programme in Smart Crop Protection
Output statusPublished
Publication dates
Online22 Feb 2017
PrintJun 2017
Publication process dates
AcceptedJun 2017
PublisherSpringer
ISSN1385-2256

Permalink - https://repository.rothamsted.ac.uk/item/8w927/detection-of-biotic-and-abiotic-stresses-in-crops-by-using-hierarchical-self-organizing-classifiers

Restricted files

Publisher's version

Under embargo indefinitely

267 total views
4 total downloads
1 views this month
0 downloads this month