ASSOCIATE
publications: Orcid
personal details and research activity: People
Curriculum Vitae
In my research journey, I have focused on the intersection between artificial intelligence and non-invasive technologies for the early diagnosis of phytopathologies, with particular attention to Botrytis cinerea. This interest stems from a multidisciplinary background that integrates expertise in plant biology, advanced imaging techniques, and predictive modeling.
During my PhD, I initiated an in-depth study on the use of PAM fluorometry and pulsed thermography to detect early stress signals associated with fungal infection. These techniques, combined with machine learning and deep learning algorithms, have shown significant potential in identifying physiological patterns altered before the visible appearance of symptoms. My work has included the design of greenhouse experimental protocols, the acquisition and pre-processing of multispectral and thermal data, and the development of predictive models based on convolutional neural networks and traditional classifiers.
In parallel, I conducted a systematic literature review on the application of AI techniques for B. cinerea detection, contributing to the definition of the state of the art and the identification of current research gaps—especially concerning the integration of data from multiple sensor sources.
Overall, my research activities fit within a broader vision of precision agriculture, aimed at promoting a sustainable and timely approach to disease management, reducing the use of pesticides, and improving crop quality.