A Computation Method Based on the Combination of Chlorophyll Fluorescence Parameters to Improve the Discrimination of Visually Similar Phenotypes Induced by Bacterial Virulence Factors

Plant disease symptom segmentation in chlorophyll fluorescence imaging with a synthetic dataset

Despite the wide use of computer vision methods in plant health monitoring, little attention is paid to segmenting the diseased leaf area at its early stages. It can be explained by the lack of datasets of plant images with annotated disease lesions. We propose a novel methodology to generate fluorescent images of diseased plants with an automated lesion annotation. We demonstrate that a U-Net model aiming to segment disease lesions on fluorescent images of plant leaves can be efficiently trained purely by a synthetically generated dataset. The trained model showed 0.793% recall and 0.723% average precision against an empirical fluorescent test dataset. Creating and using such synthetic data can be a powerful technique to facilitate the application of deep learning methods in precision crop protection. Moreover, our method of generating synthetic fluorescent images is a way to improve the generalization ability of deep learning models.

Improving Common Bacterial Blight Phenotyping by Using Rub Inoculation and Machine Learning: Cheaper, Better, Faster, Stronger

Accurate assessment of plant symptoms plays a key role for measuring the impact of pathogens during plant-pathogen interaction. Common bacterial blight caused by Xanthomonas phaseoli pv. phaseoli and X. citri pv. fuscans is a major threat to common bean. The pathogenicity of these bacteria is variable among strains and depends mainly on a type III secretion system and associated type III effectors such as transcription activator-like effectors. Because the impact of a single gene is often small and difficult to detect, a discriminating methodology is required to distinguish the slight phenotype changes induced during the progression of the disease. Here, we compared two different inoculation and symptom assessment methods for their ability to distinguish two tal mutants from their corresponding wild-type strains. Interestingly, rub inoculation of the first leaves combined with symptom assessment by machine learning-based imaging allowed significant distinction between wild-type and mutant strains. By contrast, dip inoculation of first-trifoliate leaves combined with chlorophyll fluorescence imaging did not differentiate the strains. Furthermore, the new method developed here led to the miniaturization of pathogenicity tests and significant time savings.

The Impact of LED Lighting Spectra in a Plant Factory on the Growth, Physiological Traits and Essential Oil Content of Lemon Balm (Melissa officinalis)

With the recent development of LED lighting systems for plant cultivation, the use of vertical farming under controlled conditions is attracting increased attention. This study investigated the impact of a number of LED light spectra (red, blue, green and white) on the growth, development and essential oil content of lemon balm (Melissa officinalis), a herb and pharmaceutical plant species used across the world. White light and red-rich light spectra gave the best outputs in terms of impact on the growth and yield. For blue-rich spectra, the development and yield was lower despite having a significant impact on the photosynthesis activity, including Fv/Fm and NDVI values. For the blue-rich spectra, a peak wavelength of 450 mn was better than that of 435 nm. The results have practical value in terms of increased yield and the reduction of electricity consumption under controlled environmental conditions for the commercial production of lemon balm.