Early warning and diagnostic visualization of Sclerotinia infected tomato based on hyperspectral imaging

This research explored the feasibility of early warning and diagnostic visualization of Sclerotinia infected tomato by using hyperspectral imaging technology. Healthy tomato plants and tomato plants with Sclerotinia sclerotiorum were cultivated, and hyperspectral images at 400-1000 nm were collected from healthy and infected tomato leaves at 1, 3, 5, and 7 days of incubation. After preprocessing the spectra with first derivative (FD), second derivative (SD), standard normal variant (SNV), and multiplicative scatter correction (MSC) partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were used to construct tomato sclerotinia identification model and select the best preprocessing method. On this basis, two band screening methods, competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA), were introduced to reduce data redundancy and improve the model's prediction accuracy. The results showed that the accuracy of the validation sets and operation speed of the CARS-PLS and CARS-SVM models were 87.88% and 1.8 s, and 87.95% and 1.78 s, respectively. The experiment was based on the SNV-CARS-SVM prediction model combined with image processing, spectral extraction, and visualization analysis methods to create diagnostic visualization software, which opens a new avenue to the implementation of online monitoring and early warning system for sclerotinia infected tomato.

Automated summary

This research explored the feasibility of using hyperspectral imaging technology for early warning and diagnostic visualization of Sclerotinia infected tomato. PLS-DA and SVM were used to construct identification models, and two band screening methods were introduced to improve prediction accuracy.