Preliminary Analysis of Biotic and Abiotic Stress on Tomato Plants Using Impedance Measurements and Time Series Clustering

This paper presents a study on the application of time series clustering to differentiate biotic and abiotic stresses in tomato plants using stem impedance measurements. Specifically, it explores the effectiveness of the k-means clustering algorithm in classifying plants under healthy conditions, drought-induced water deprivation, and Fusarium fungal infection. Over a period from March 9, 2024, to April 18, 2024, six tomato plants were monitored for changes in stem frequency, a parameter proportional to electrical impedance. The study reveals that while the algorithm could accurately identify plants under water stress, it struggled to distinguish between healthy and Fusarium-infected plants. This indicates the potential of impedance measurements as a non-invasive tool for early stress detection, although further refinement with additional environmental data and larger sample sizes is necessary. Future research will focus on enhancing the algorithm's accuracy by incorporating more diverse datasets, aiming to contribute to the development of an autonomous plant monitoring system for smart agriculture applications.