Kiwi Plant Canker Diagnosis Using Hyperspectral Signal Processing and Machine Learning: Detecting Symptoms Caused by Pseudomonas syringae pv. actinidiae

Scientific and technological advances in the development of sustainable disease management tools: a case study on kiwifruit bacterial canker

Plant disease outbreaks are increasing in a world facing climate change and globalized markets, representing a serious threat to food security. Kiwifruit Bacterial Canker (KBC), caused by the bacterium Pseudomonas syringae pv. actinidiae (Psa), was selected as a case study for being an example of a pandemic disease that severely impacted crop production, leading to huge economic losses, and for the effort that has been made to control this disease. This review provides an in-depth and critical analysis on the scientific progress made for developing alternative tools for sustainable KBC management. Their status in terms of technological maturity is discussed and a set of opportunities and threats are also presented. The gradual replacement of susceptible kiwifruit cultivars, with more tolerant ones, significantly reduced KBC incidence and was a major milestone for Psa containment - which highlights the importance of plant breeding. Nonetheless, this is a very laborious process. Moreover, the potential threat of Psa evolving to more virulent biovars, or resistant lineages to existing control methods, strengthens the need of keep on exploring effective and more environmentally friendly tools for KBC management. Currently, plant elicitors and beneficial fungi and bacteria are already being used in the field with some degree of success. Precision agriculture technologies, for improving early disease detection and preventing pathogen dispersal, are also being developed and optimized. These include hyperspectral technologies and forecast models for Psa risk assessment, with the latter being slightly more advanced in terms of technological maturity. Additionally, plant protection products based on innovative formulations with molecules with antibacterial activity against Psa (e.g., essential oils, phages and antimicrobial peptides) have been validated primarily in laboratory trials and with few compounds already reaching field application. The lessons learned with this pandemic disease, and the acquired scientific and technological knowledge, can be of importance for sustainably managing other plant diseases and handling future pandemic outbreaks.

Enhancing host-pathogen phenotyping dynamics: early detection of tomato bacterial diseases using hyperspectral point measurement and predictive modeling

Early diagnosis of plant diseases is needed to promote sustainable plant protection strategies. Applied predictive modeling over hyperspectral spectroscopy (HS) data can be an effective, fast, cost-effective approach for improving plant disease diagnosis. This study aimed to investigate the potential of HS point-of-measurement (POM) data for in-situ, non-destructive diagnosis of tomato bacterial speck caused by Pseudomonas syringae pv. tomato (Pst), and bacterial spot, caused by Xanthomonas euvesicatoria (Xeu), on leaves (cv. cherry). Bacterial artificial infection was performed on tomato plants at the same phenological stage. A sensing system composed by a hyperspectral spectrometer, a transmission optical fiber bundle with a slitted probe and a white light source were used for spectral data acquisition, allowing the assessment of 3478 spectral points. An applied predictive classification model was developed, consisting of a normalizing pre-processing strategy allied with a Linear Discriminant Analysis (LDA) for reducing data dimensionality and a supervised machine learning algorithm (Support Vector Machine - SVM) for the classification task. The predicted model achieved classification accuracies of 100% and 74% for Pst and Xeu test set assessments, respectively, before symptom appearance. Model predictions were coherent with host-pathogen interactions mentioned in the literature (e.g., changes in photosynthetic pigment levels, production of bacterial-specific molecules, and activation of plants' defense mechanisms). Furthermore, these results were coherent with visual phenotyping inspection and PCR results. The reported outcomes support the application of spectral point measurements acquired in-vivo for plant disease diagnosis, aiming for more precise and eco-friendly phytosanitary approaches.

Detection, Diagnosis, and Preventive Management of the Bacterial Plant Pathogen Pseudomonas syringae

Plant diseases caused by the pathogen Pseudomonas syringae are serious problems for various plant species worldwide. Accurate detection and diagnosis of P. syringae infections are critical for the effective management of these plant diseases. In this review, we summarize the current methods for the detection and diagnosis of P. syringae, including traditional techniques such as culture isolation and microscopy, and relatively newer techniques such as PCR and ELISA. It should be noted that each method has its advantages and disadvantages, and the choice of each method depends on the specific requirements, resources of each laboratory, and field settings. We also discuss the future trends in this field, such as the need for more sensitive and specific methods to detect the pathogens at low concentrations and the methods that can be used to diagnose P. syringae infections that are co-existing with other pathogens. Modern technologies such as genomics and proteomics could lead to the development of new methods of highly accurate detection and diagnosis based on the analysis of genetic and protein markers of the pathogens. Furthermore, using machine learning algorithms to analyze large data sets could yield new insights into the biology of P. syringae and novel diagnostic strategies. This review could enhance our understanding of P. syringae and help foster the development of more effective management techniques of the diseases caused by related pathogens.