Electrophysiological assessment of plant status outside a Faraday cage using supervised machine learning

Daniel Tran,Elena Najdenovska,Marco Mazza,Fabien Dutoit,Cédric Camps,Nigel Wallbridge,Laura Elena Raileanu,Carrol Plummer

doi:10.1038/s41598-019-53675-4

Abstract

Living organisms have evolved complex signaling networks to drive appropriate physiological processes in response to changing environmental conditions. Amongst them, electric signals are a universal method to rapidly transmit information. In animals, bioelectrical activity measurements in the heart or the brain provide information about health status. In plants, practical measurements of bioelectrical activity are in their infancy and transposition of technology used in human medicine could therefore, by analogy provide insight about the physiological status of plants. This paper reports on the development and testing of an innovative electrophysiological sensor that can be used in greenhouse production conditions, without a Faraday cage, enabling real-time electric signal measurements. The bioelectrical activity is modified in response to water stress conditions or to nycthemeral rhythm. Furthermore, the automatic classification of plant status using supervised machine learning allows detection of these physiological modifications. This sensor represents an efficient alternative agronomic tool at the service of producers for decision support or for taking preventive measures before initial visual symptoms of plant stress appear.

Highlights

Living organisms have evolved complex signaling networks to drive appropriate physiological processes in response to changing environmental conditions
We present the results of long-term recordings of bioelectrical activity of soilless cultivated tomatoes in a water deficit regimen, in a commercial greenhouse setting without use of a Faraday cage
The results of this study show that, with both appropriate instrumentation and methods for data processing and analysis, it is possible to gauge, with a high-degree of confidence, plant water status using electrophysiological measurements in natural growing conditions i.e. without the use of a Faraday cage

Summary

Introduction

Living organisms have evolved complex signaling networks to drive appropriate physiological processes in response to changing environmental conditions. Plants have evolved several paths for long-range signal transmission between cells, tissues and organs in order to adapt their metabolism and development in response to a changing environment This long-distance communication can be triggered by biotic or abiotic stimuli that are sensed locally by a few cells and translated into mobile signals such as small molecules, peptides, second messengers or phytohormones[3,4]. Plants require a coordinated and timely response in above-ground and below-ground organs to cope with the changing need to take up and preserve water This is mediated by a complex signalling network, which includes, amongst others, electric signals. Using electrical signals as the basis for a sensor to measure real-time plant water status is of great interest as an agronomic tool that enables continuous and non-destructive measurements to control irrigation

Methods

Results

Conclusion