Abstract:
Advanced detection of disease within crops can help minimize potential production losses,
decrease environmental risk, and reduce the cost of farming. The objective of this study was the
detection of early blight (Alternaria solani) in potato (Solanum tuberosum) plants at two
different growth stages using a handheld hyperspectral spectroradiometer. Hyperspectral
reflectance spectra were captured 10 times over five weeks from plants grown to the vegetative
and tuber bulking growth stages. The spectra were analyzed using principal component analysis
(PCA) and spectral change (ratio) analysis. PCA successfully distinguished more heavily
diseased plants from healthy and minimally diseased plants using two principal components.
Spectral change (ratio) analysis found optimal wavelengths (505, 510, 640, 665, 690, 750, and
935 nm) which were most sensitive to early blight infection. ANOVA results indicated a highly
significant difference (p < 0.0001) between disease rating group means. Comparisons of diseased
plants versus healthy plants using Fisher's LSD revealed more heavily diseased plants were
significantly different from healthy plants. The results of this study demonstrated the capability
of the PCA and spectral change (ratio) analysis techniques for detection of early blight disease in
potato plants.
|
