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

This study investigates the use of stem impedance measurements combined with time series clustering to distinguish biotic and abiotic stress in tomato plants. Unsupervised learning (k-means with Dynamic Time Warping) was applied to experimental data collected under controlled greenhouse conditions. Results show a clear discrimination of drought stress, while Fusarium infection was more difficult to distinguish from healthy plants, highlighting the potential of impedance-based monitoring for smart agriculture applications.