When Plants Respond: Electrophysiology and Machine Learning for Green Monitoring Systems

TL;DR

This paper demonstrates how electrophysiological signals from plants, recorded via a wearable device and analyzed with AutoML, can effectively monitor environmental conditions in real-world outdoor settings.

Contribution

It introduces a novel biohybrid system using plant electrophysiology and machine learning for sustainable environmental monitoring in uncontrolled environments.

Findings

High classification accuracy with macro F1 scores up to 95%

AutoML outperforms manual feature tuning

Effective long-term monitoring in outdoor conditions

Abstract

Living plants, while contributing to ecological balance and climate regulation, also function as natural sensors capable of transmitting information about their internal physiological states and surrounding conditions. This rich source of data provides potential for applications in environmental monitoring and precision agriculture. With integration into biohybrid systems, we establish novel channels of physiological signal flow between living plants and artificial devices. We equipped *Hedera helix* with a plant-wearable device called PhytoNode to continuously record the plant's electrophysiological activity. We deployed plants in an uncontrolled outdoor environment to map electrophysiological patterns to environmental conditions. Over five months, we collected data that we analyzed using state-of-the-art and automated machine learning (AutoML). Our classification models achieve high performance, reaching macro F1 scores of up to 95 percent in binary tasks. AutoML approaches outperformed manual tuning, and selecting subsets of statistical features further improved accuracy. Our biohybrid living system monitors the electrophysiology of plants in harsh, real-world conditions. This work advances scalable, self-sustaining, and plant-integrated living biohybrid systems for sustainable environmental monitoring.