Embedded Deep Learning for Bio-hybrid Plant Sensors to Detect Increased Heat and Ozone Levels

2025-09-29

AI Summary

Real-time, low-power, on-device monitoring of ambient temperature and ozone concentration remains challenging. Method: This study proposes a biohybrid sensing paradigm that leverages the electrophysiological signals of live *Hedera helix* (English ivy) tissue as a natural transducer, integrated with a custom low-power embedded platform (PhytoNode) and a lightweight deep learning model for edge-based signal acquisition, adaptive feature learning, and multi-factor classification. Unlike conventional synthetic sensors, it models plant membrane potential dynamics as intrinsic environmental disturbance responses, employing time-frequency feature extraction and model pruning to enable end-to-end inference on resource-constrained edge devices. Contribution/Results: Experimental evaluation demonstrates 0.98 detection accuracy for temperature and ozone variations, effectively suppressing confounding effects from diurnal rhythms and inter-individual variability. The system exhibits strong robustness, cross-species scalability, and practical deployability.

Technology Category

• Machine Learning: Bio-inspired Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

We present a bio-hybrid environmental sensor system that integrates natural plants and embedded deep learning for real-time, on-device detection of temperature and ozone level changes. Our system, based on the low-power PhytoNode platform, records electric differential potential signals from Hedera helix and processes them onboard using an embedded deep learning model. We demonstrate that our sensing device detects changes in temperature and ozone with good sensitivity of up to 0.98. Daily and inter-plant variability, as well as limited precision, could be mitigated by incorporating additional training data, which is readily integrable in our data-driven framework. Our approach also has potential to scale to new environmental factors and plant species. By integrating embedded deep learning onboard our biological sensing device, we offer a new, low-power solution for continuous environmental monitoring and potentially other fields of application.

Problem

• Detect temperature changes using plant-based bio-hybrid sensors
• Monitor ozone level variations through embedded deep learning
• Address environmental monitoring with low-power continuous sensing solutions

Innovation

• Embedded deep learning for bio-hybrid plant sensors
• On-device signal processing using PhytoNode platform
• Scalable data-driven framework for environmental monitoring