Plant Electrical Signal Classification Based on Waveform Similarity

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 (Phaseolus vulgaris 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.

Clivia biosensor: Soil moisture identification based on electrophysiology signals with deep learning

Research has shown that plants have the ability to detect environmental changes and generate electrical signals in response. These electrical signals can regulate the physiological state of plants and produce corresponding feedback. This suggests that plants have the potential to be used as biosensors for monitoring environmental information. However, there are current challenges in linking environmental information with plant electrical signals, especially in collecting and classifying the corresponding electrical signals under soil moisture gradients. This study documented the electrical signals of clivia under different soil moisture gradients and created a dataset for classifying electrical signals. Subsequently, we proposed a lightweight convolutional neural network (CNN) model (PlantNet) for classifying the electrical signal dataset. Compared to traditional CNN models, our model achieved optimal classification performance with the lowest computational resource consumption. The model achieved an accuracy of 99.26%, precision of 99.31%, recall of 92.26%, F1-score of 99.21%, with 0.17M parameters, a size of 7.17MB, and 14.66M FLOPs. Therefore, this research provides scientific evidence for the future development of plants as biosensors for detecting soil moisture, and offers insight into developing plants as biosensors for detecting signals such as ozone, PM2.5, Volatile Organic Compounds(VOCs), and more. These studies are expected to drive the development of environmental monitoring technology and provide new pathways for better understanding the interaction between plants and the environment.

Multiclass classification of environmental chemical stimuli from unbalanced plant electrophysiological data

Plant electrophysiological response contains useful signature of its environment and health which can be utilized using suitable statistical analysis for developing an inverse model to classify the stimulus applied to the plant. In this paper, we have presented a statistical analysis pipeline to tackle a multiclass environmental stimuli classification problem with unbalanced plant electrophysiological data. The objective here is to classify three different environmental chemical stimuli, using fifteen statistical features, extracted from the plant electrical signals and compare the performance of eight different classification algorithms. A comparison using reduced dimensional projection of the high dimensional features via principal component analysis (PCA) has also been presented. Since the experimental data is highly unbalanced due to varying length of the experiments, we employ a random under-sampling approach for the two majority classes to create an ensemble of confusion matrices to compare the classification performances. Along with this, three other multi-classification performance metrics commonly used for unbalanced data viz. balanced accuracy, F1-score and Matthews correlation coefficient have also been analyzed. From the stacked confusion matrices and the derived performance metrics, we choose the best feature-classifier setting in terms of the classification performances carried out in the original high dimensional vs. the reduced feature space, for this highly unbalanced multiclass problem of plant signal classification due to different chemical stress. Difference in the classification performances in the high vs. reduced dimensions are also quantified using the multivariate analysis of variance (MANOVA) hypothesis testing. Our findings have potential real-world applications in precision agriculture for exploring multiclass classification problems with highly unbalanced datasets, employing a combination of existing machine learning algorithms. This work also advances existing studies on environmental pollution level monitoring using plant electrophysiological data.

Building bridges: mycelium-mediated plant-plant electrophysiological communication

Whether through root secretions or by emitting volatile organic compounds, plant communication has been well-documented. While electrical activity has been documented in plants and mycorrhizal bodies on the individual and ramet, electrical propagation as a means of communication between plants has been hypothesized but understudied. This study aimed to test the hypothesis that plants can communicate with one another electrically via conductively isolated mycelial pathways. We created a bio-electric circuit linking two plants using a mycelial network grown from a blend of mycorrhizal fungi which was directly inoculated onto potato dextrose agar, or onto the host plants placed on the agar. The mycelium that grew was forced to cross, or "bridge," an air gap between the two islands of agar - thus forming the isolated conductive pathway between plants. Using this plant-fungal biocircuit we assessed electrical propagation between Pisum sativum and Cucumis sativus. We found that electrical signals were reliably conducted across the mycelial bridges from one plant to another upon the induction of a wound response. Our findings provide evidence that mechanical input can be communicated between plant species and opens the door to testing how this information can affect plant and fungal physiology.

Classification of various nutrient deficiencies in tomato plants through electrophysiological signal decomposition and sample space reduction

Plants leave testimonies of undergoing physical state by depicting distinct variations in their electrophysiological data. Adequate nutrition of plants signifies their role in the growth and a plentiful harvest. Plant signal data carries enough information to detect and analyse nutrient deficiency. Classification of nutrient deficiencies through signal decomposition and bilevel measurements has not been reported earlier. The proposed work explores tomato plants in four-time cycles (Early Morning, Morning, After Noon, Night) of macronutrients Calcium (Ca), Nitrogen (N) and micronutrients Manganese (Mn), Iron (Fe). Using the Empirical Mode Decomposition method (EMD), signals are decomposed into Intrinsic Mode Functions (IMF) in 10-levels. Further, Intrinsic mode functions are grouped into two clusters to extract descriptive data statistics and bi-level measurements. Then a novel sample selection method is proposed to achieve a better classification rate by reducing sample space. A binary classification model is built to train and test 15 features individually using discriminant analysis and naïve-Bayes classifier variants. The reported results achieved a classification rate up to 98% after 5-fold cross-validation. Attained findings endorse novel pathways for detection and classification of nutrient deficiencies in the early stages, consequently promoting prevention and treatment approaches earliest to the appearance of symptoms, also helping to enhance plant growth.

Influence of Burning-Induced Electrical Signals on Photosynthesis in Pea Can Be Modified by Soil Water Shortage

Local damage to plants can induce fast systemic physiological changes through generation and propagation of electrical signals. It is known that electrical signals influence numerous physiological processes including photosynthesis; an increased plant tolerance to actions of stressors is a result of these changes. It is probable that parameters of electrical signals and fast physiological changes induced by these signals can be modified by the long-term actions of stressors; however, this question has been little investigated. Our work was devoted to the investigation of the parameters of burning-induced electrical signals and their influence on photosynthesis under soil water shortage in pea seedlings. We showed that soil water shortage decreased the amplitudes of the burning-induced depolarization signals (variation potential) and the magnitudes of photosynthetic inactivation (decreasing photosynthetic CO₂ assimilation and linear electron flow and increasing non-photochemical quenching of the chlorophyll fluorescence and cyclic electron flow around photosystem I) caused by these signals. Moreover, burning-induced hyperpolarization signals (maybe, system potentials) and increased photosynthetic CO₂ assimilation could be observed under strong water shortage. It was shown that the electrical signal-induced increase of the leaf stomatal conductance was a potential mechanism for the burning-induced activation of photosynthetic CO₂ assimilation under strong water shortage; this mechanism was not crucial for photosynthetic response under control conditions or weak water shortage. Thus, our results show that soil water shortage can strongly modify damage-induced electrical signals and fast physiological responses induced by these signals.

Machine Learning for Automatic Classification of Tomato Ripening Stages Using Electrophysiological Recordings

The physiological processes underlying fruit ripening can lead to different electrical signatures at each ripening stage, making it possible to classify tomato fruit through the analysis of electrical signals. Here, the electrical activity of tomato fruit (Solanum lycopersicum var. cerasiforme) during ripening was investigated as tissue voltage variations, and Machine Learning (ML) techniques were used for the classification of different ripening stages. Tomato fruit was harvested at the mature green stage and placed in a Faraday's cage under laboratory-controlled conditions. Two electrodes per fruit were inserted 1 cm apart from each other. The measures were carried out continuously until the entire fruits reached the light red stage. The time series were analyzed by the following techniques: Fast Fourier Transform (FFT), Wavelet Transform, Power Spectral Density (PSD), and Approximate Entropy. Descriptive analysis from FFT, PSD, and Wavelet Transform were used for PCA (Principal Component Analysis). Finally, ApEn, PCA1, PCA2, and PCA3 were obtained. These features were used in ML analyses for looking for classifiable patterns of the three different ripening stages: mature green, breaker, and light red. The results showed that it is possible to classify the ripening stages using the fruit's electrical activity. It was also observed, using precision, sensitivity, and F1-score techniques, that the breaker stage was the most classifiable among all stages. It was found a more accurate distinction between mature green × breaker than between breaker × light red. The ML techniques used seem to be a novel tool for classifying ripening stages. The features obtained from electrophysiological time series have the potential to be used for supervised training, being able to help in more accurate classification of fruit ripening stages.

Electrical Signals, Plant Tolerance to Actions of Stressors, and Programmed Cell Death: Is Interaction Possible?

In environmental conditions, plants are affected by abiotic and biotic stressors which can be heterogenous. This means that the systemic plant adaptive responses on their actions require long-distance stress signals including electrical signals (ESs). ESs are based on transient changes in the activities of ion channels and H⁺-ATP-ase in the plasma membrane. They influence numerous physiological processes, including gene expression, phytohormone synthesis, photosynthesis, respiration, phloem mass flow, ATP content, and many others. It is considered that these changes increase plant tolerance to the action of stressors; the effect can be related to stimulation of damages of specific molecular structures. In this review, we hypothesize that programmed cell death (PCD) in plant cells can be interconnected with ESs. There are the following points supporting this hypothesis. (i) Propagation of ESs can be related to ROS waves; these waves are a probable mechanism of PCD initiation. (ii) ESs induce the inactivation of photosynthetic dark reactions and activation of respiration. Both responses can also produce ROS and, probably, induce PCD. (iii) ESs stimulate the synthesis of stress phytohormones (e.g., jasmonic acid, salicylic acid, and ethylene) which are known to contribute to the induction of PCD. (iv) Generation of ESs accompanies K⁺ efflux from the cytoplasm that is also a mechanism of induction of PCD. Our review argues for the possibility of PCD induction by electrical signals and shows some directions of future investigations in the field.

Stochastic Spatial Heterogeneity in Activities of H+-ATP-Ases in Electrically Connected Plant Cells Decreases Threshold for Cooling-Induced Electrical Responses

H⁺-ATP-ases, which support proton efflux through the plasma membrane, are key molecular transporters for electrogenesis in cells of higher plants. Initial activities of the transporters can influence the thresholds of generation of electrical responses induced by stressors and modify other parameters of these responses. Previously, it was theoretically shown that the stochastic heterogeneity of individual cell thresholds for electrical responses in a system of electrically connected neuronal cells can decrease the total threshold of the system (“diversity-induced resonance”, DIR). In the current work, we tested a hypothesis about decreasing the thresholds of generation of cooling-induced electrical responses in a system of electrically connected plant cells with increasing stochastic spatial heterogeny in the initial activities of H⁺-ATP-ases in these cells. A two-dimensional model of the system of electrically connected excitable cells (simple imitation of plant leaf), which was based on a model previously developed in our works, was used for the present investigation. Simulation showed that increasing dispersion in the distribution of initial activities of H⁺-ATP-ases between cells decreased the thresholds of generation of cooling-induced electrical responses. In addition, the increasing weakly influenced the amplitudes of electrical responses. Additional analysis showed two different mechanisms of the revealed effect. The increasing spatial heterogeneity in activities of H⁺-ATP-ases induced a weak positive shift of the membrane potential at rest. The shift decreased the threshold of electrical response generation. However, the decreased threshold induced by increasing the H⁺-ATP-ase activity heterogeneity was also observed after the elimination of the positive shift. The result showed that the “DIR-like” mechanism also participated in the revealed effect. Finally, we showed that the standard deviation of the membrane potentials before the induction of action potentials could be used for the estimation of thresholds of cooling-induced plant electrical responses. Thus, spatial heterogeneity in the initial activities of H⁺-ATP-ases can be a new regulatory mechanism influencing the generation of electrical responses in plants under actions of stressors.

Comparison on the Nutrient Plunder Capacity of Orychophragmus violaceus and Brassica napus L. Based on Electrophysiological Information

The nutrient metabolism, growth and development of plants are strongly affected by its nutrient plunder, and plants have different adaptive mechanisms to low-nutrient environments. The electrophysiological activities involve almost all life processes of plants. In this study, the active transport flow of nutrient (NAF) and nutrient plunder capacity (NPC) of plants were defined based on leaf intrinsic impedance (IZ), capacitive reactance (IXc), inductive reactance (IXL) and capacitance (IC) to evaluate the nutrient plunder capacity of plants for the first time. The results indicate that Orychophragmus violaceus had higher (p < 0.01) NPC and IC and lower (p < 0.01) IR, IXc, IXL and IZ as compared to Brassica napus L., which supports a superior ion affinity and that it could be better adapted to low-nutrient environments. UAF and NPC of plants exhibited good correlations with crude protein, crude ash and water content, and precisely revealed the plunder capacity and adaptive strategies of plants to nutrients. The present work highlights that O. violaceus had superior NPC and ion affinity compared with B. napus, and provided a novel, rapid, reliable method based on the plant’s electrophysiological information for real-time determination of the nutrient plunder capacity of plants.

Plant's electrophysiological information manifests the composition and nutrient transport characteristics of membrane proteins

Almost all life activities of plants are accompanied by electrophysiological information. Plant's electrical parameters are considered to be the fastest response to environment. In this study, the theoretically intrinsic relationships between the clamping force and leaf resistance (R) and inductive reactance (XL) were revealed as 3-parameter exponential decay based on bioenergetics for the first time. The intrinsic resistance (IR), capacitive reactance (IXc), inductive reactance (IXL), impedance (IZ), and capacitance (IC) in plant leaves were successfully monitored. The nutrient flux per unit area (UNF), nutrient transfer rate (NTR) and nutrient transport capacity (NTC) in plants based on IR, IXc, IXL, IZ and IC were defined to reflect nutrient transport characteristics. The results indicate that IXc and IXL could be used to manifest the relative composition characteristics of cell membrane proteins, and are inversely proportional to the amount of surface and binding proteins that induce membrane Xc and XL in plant leaves, respectively. UNF, NTR or NTC exhibited good correlations with crude protein or crude ash, and accurately revealed the nutrient transport strategies of tested plants and their diversity. This study highlights that plant's electrophysiological information could effectively manifest the composition and nutrient transport characteristics of membrane proteins in plant cells.

A Plant's Electrical Parameters Indicate Its Physiological State: A Study of Intracellular Water Metabolism

Almost all of a plant’s life activities involve electrochemical reactions. Plant electrical parameters respond quickly to environmental changes and are closely related to physiological activities. In this study, the theoretical intrinsic relationships between clamping force and leaf impedance (Z) or capacitive reactance (Xc) and capacitance (C) were revealed as 3-parameter exponential decay and linear models based on bioenergetics, respectively, for the first time. Leaf electrical characteristics including intrinsic impedance (IZ), capacitive reactance (IXc), capacitance (IC) and specific effective thickness (d) were successfully detected using the above-mentioned relationships and were used to manifest plant metabolic activity. The intracellular water-holding capacity (IWHC), water-use efficiency (IWUE), water-holding time (IWHT) and water transfer rate (WTR) of plant leaves were defined on the basis of IZ, IXc, IC and d, and applied to reflect the intracellular water metabolism. The results demonstrated that the leaves of Broussonetia papyrifera plants grown in agricultural soil had higher IC, d, IWHC, WTR, water content values and lower IZ, IXc values than those grown in moderately rocky desertified soil. The leaf IC, d, IWHC, WTR and water content values of herbaceous plants were higher than those of woody plants. Solanum tuberosum L. had higher leaf IC, d, IWHC and WTR values, but exhibited lower IZ, IXc, IWUE and IWHT values than Capsicum annuum L. This study highlighted that a plant’s electrical parameters based on bioenergetics clearly indicate its physiological process—e.g., the intracellular water metabolism.

Burning-induced electrical signals influence broadband reflectance indices and water index in pea leaves

Electrical signals (ESs) can be induced by local action of stressors in plants; they influence numerous physiological processes (photosynthesis, transpiration, respiration, genes expression, synthesis of phytohormones, etc.) and, thereby, induce a systemic adaptation response. Development of optical methods of a remote sensing of this response can be important for agricultural and ecological monitoring. Preliminarily, we showed (Sukhova et al., Plant Sign Behav 2019; 14:e1610301) that burning-induced ESs induced changes in leaf reflectance at broad spectral bands (400-500, 500-600, 600-700, and 700-800 nm). The aims of the present work were (i) investigation of ESs influence on difference reflectance indices (RIs) calculated on the basis of these broad spectral bands and (ii) analysis of connection of the indices with water content in plants. Pea seedlings were investigated. ESs were induced by burning of the first mature leaf; ESs had high amplitudes in the second leaf and had low amplitudes in the fourth leaf. It was shown that ESs induced significant changes in RIs, which were calculated on basis of intensities of the reflected light at (i) 400-500 and 600-700 nm, (ii) 500-600 and 700-800 nm, and (iii) 600-700 and 700-800 nm. The effect was strong in the second leaf and weak in the fourth leaf; that is, the response was dependent on the magnitude of ESs. ESs-induced changes in RI were strongly connected with ESs-induced decrease of leaf water content which was estimated on basis of decrease of water index. Thus, broadband RIs can be used for revealing the ESs-induced systemic stress response in plants.

PlantES: A Plant Electrophysiological Multi-Source Data Online Analysis and Sharing Platform

At present, plant electrophysiological data volumes and complexity are increasing rapidly. It causes the demand for efficient management of big data, data sharing among research groups, and fast analysis. In this paper, we proposed PlantES (Plant Electrophysiological Data Sharing), a distributed computing-based prototype system that can be used to store, manage, visualize, analyze, and share plant electrophysiological data. We deliberately designed a storage schema to manage the multi-source plant electrophysiological data by integrating distributed storage systems HDFS and HBase to access all kinds of files efficiently. To improve the online analysis efficiency, parallel computing algorithms on Spark were proposed and implemented, e.g., plant electrical signals extraction method, the adaptive derivative threshold algorithm, and template matching algorithm. The experimental results indicated that Spark efficiently improves the online analysis. Meanwhile, the online visualization and sharing of multiple types of data in the web browser were implemented. Our prototype platform provides a solution for web-based sharing and analysis of plant electrophysiological multi-source data and improves the comprehension of plant electrical signals from a systemic perspective.

Electrical Signaling, Photosynthesis and Systemic Acquired Acclimation

Electrical signaling in higher plants is required for the appropriate intracellular and intercellular communication, stress responses, growth and development. In this review, we have focus on recent findings regarding the electrical signaling, as a major regulator of the systemic acquired acclimation (SAA) and the systemic acquired resistance (SAR). The electric signaling on its own cannot confer the required specificity of information to trigger SAA and SAR, therefore, we have also discussed a number of other mechanisms and signaling systems that can operate in combination with electric signaling. We have emphasized the interrelation between ionic mechanism of electrical activity and regulation of photosynthesis, which is intrinsic to a proper induction of SAA and SAR. In a special way, we have summarized the role of non-photochemical quenching and its regulator PsbS. Further, redox status of the cell, calcium and hydraulic waves, hormonal circuits and stomatal aperture regulation have been considered as components of the signaling. Finally, a model of light-dependent mechanisms of electrical signaling propagation has been presented together with the systemic regulation of light-responsive genes encoding both, ion channels and proteins involved in regulation of their activity. Due to space limitations, we have not addressed many other important aspects of hormonal and ROS signaling, which were presented in a number of recent excellent reviews.

Mathematical Models of Electrical Activity in Plants

Electrical activity plays an important role in plant life; in particular, electrical responses can participate in the reception of the action of stressors (local electrical responses and oscillations) and signal transduction into unstimulated parts of the plant (action potential, variation potential and system potential). Understanding the mechanisms of electrical responses and subsequent changes in physiological processes and the prediction of plant responses to stressors requires the elaboration of mathematical models of electrical activity in plant organisms. Our review describes approaches to the simulation of plant electrogenesis and summarizes current models of electrical activity in these organisms. It is shown that there are numerous models of the generation of electrical responses, which are based on various descriptions (from modifications of the classical Hodgkin-Huxley model to detailed models, which consider ion transporters, regulatory processes, buffers, etc.). A moderate number of works simulate the propagation of electrical signals using equivalent electrical circuits, systems of excitable elements with local electrical coupling and descriptions of chemical signal propagation. The transmission of signals from a plasma membrane to intracellular compartments (endoplasmic reticulum, vacuole) during the generation of electrical responses is much less modelled. Finally, only a few works simulate plant physiological changes that are connected with electrical responses or investigate the inverse problem: reconstruction of the type and parameters of stimuli through the analysis of electrical responses. In the conclusion of the review, we discuss future perspectives on the simulation of electrical activity in plants.