Common bean under different water availability reveals classifiable stimuli-specific signatures in plant electrome.

Plant electrophysiology has unveiled the involvement of electrical signals in the physiology and behavior of plants. Spontaneously generated bioelectric activity can be altered in response to changes in environmental conditions, suggesting that a plant's electrome may possess a distinct signature associated with various stimuli. Analyzing electrical signals, particularly the electrome, in conjunction with Machine Learning (ML) techniques has emerged as a promising approach to classify characteristic electrical signals corresponding to each stimulus. This study aimed to characterize the electrome of common bean ( L.) cv. BRS-Expedito, subjected to different water availabilities, seeking patterns linked to these stimuli. For this purpose, bean plants in the vegetative stage were subjected to the following treatments: (I) distilled water; (II) half-strength Hoagland's nutrient solution; (III) -2 MPa PEG solution; and (IV) -2 MPa NaCl solution. Electrical signals were recorded within a Faraday's cage using the MP36 electronic system for data acquisition. Concurrently, plant water status was assessed by monitoring leaf turgor variation. Leaf temperature was additionally measured. Various analyses were conducted on the electrical time series data, including arithmetic average of voltage variation, skewness, kurtosis, Probability Density Function (PDF), autocorrelation, Power Spectral Density (PSD), Approximate Entropy (ApEn), Fast Fourier Transform (FFT), and Multiscale Approximate Entropy (ApEn(s)). Statistical analyses were performed on leaf temperature, voltage variation, skewness, kurtosis, PDF µ exponent, autocorrelation, PSD β exponent, and approximate entropy data. Machine Learning analyses were applied to identify classifiable patterns in the electrical time series. Characterization of the electrome of BRS-Expedito beans revealed stimulus-dependent profiles, even when alterations in water availability stimuli were similar in terms of quality and intensity. Additionally, it was observed that the bean electrome exhibits high levels of complexity, which are altered by different stimuli, with more intense and aversive stimuli leading to drastic reductions in complexity levels. Notably, one of the significant findings was the 100% accuracy of Small Vector Machine in detecting salt stress using electrome data. Furthermore, the study highlighted alterations in the plant electrome under low water potential before observable leaf turgor changes. This work demonstrates the potential use of the electrome as a physiological indicator of the water status in bean plants.