Early Detection of Water Stress by Plant Electrophysiology: Machine Learning for Irrigation Management

2026-04-30

AI Summary

This study addresses the challenge of early detection of water stress in crops prior to the onset of visible symptoms, aiming to enable precision irrigation. To this end, the authors propose an online detection framework based on electrophysiological time-series signals from tomato plants, uniquely integrating electrophysiological sensing with automated machine learning (AutoML). The approach employs statistical feature extraction, sequential backward selection, and probability calibration to classify plant health status in real time within a 30-minute retrospective window. Evaluated on unseen data, the method achieves 92% accuracy—outperforming deep learning baselines—while substantially reducing the number of features without compromising performance. This work thus provides an effective foundation for biofeedback-driven intelligent irrigation systems.

Abstract

Purpose: Fast detection of plant stress is key to plant phenotyping, precision agriculture, and automated crop management. In particular, efficient irrigation management requires early identification of water stress to optimize resource use while maintaining crop performance. Direct physiological sensing offers the potential to detect stress responses before visible symptoms appear. Methods: In this study, we recorded electrophysiological signals from greenhouse-grown tomato plants subjected to water stress and developed a framework based on machine learning for online stress detection. The recorded time-series data were processed using a processing pipeline that includes statistical feature extraction and selection, automated machine learning or alternatively deep learning, and probability calibration. Results: Across multiple input time horizons, we found that a 30-minute look-back window strikes the best balance between rapid decision-making and classification performance. Using automated machine learning, the framework achieved classification accuracies of up to 92%, outperforming deep learning approaches. Sequential backward selection reduced the feature set while maintaining performance. Importantly, the framework detects transitions from healthy to stressed states in recordings that were not included in the training set. Conclusion: Overall, we provide a decision-support tool for farmers and establish a foundation for biofeedback-driven irrigation control to improve resource efficiency in (semi-)autonomous crop production systems.

Problem

• water stress
• early detection
• plant electrophysiology
• irrigation management
• precision agriculture

Innovation

• plant electrophysiology
• machine learning
• water stress detection
• automated irrigation
• feature selection