Water stress detection from plant electrophysiology: A machine learning framework for irrigation management

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. 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 resulting time-series data were segmented into tumbling windows of 1 min, 5 min, 30 min, 1 h and 6 h, then passed through a processing pipeline that includes statistical feature extraction and selection, automated machine learning or alternatively deep learning, and probability calibration. Across multiple input time horizons, we found that a 30-minute look-back horizon 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. Out-of-sample testing on withheld plant individuals provides methodological validation, confirming that the framework detects healthy-to-stress transitions despite inter-individual electrophysiological variability.Overall, we develop and provide a decision-support tool for agricultural practitioners and researchers and establish a foundation for biofeedback-driven irrigation control to improve resource efficiency in (semi-)autonomous crop production systems.