TY  - JOUR
AU  - Zhang, Xiaohui
AU  - Fu, Yingkai
AU  - Zhang, Chi
AU  - Yang, Jian
AU  - Zhai, Zeyu
PY  - 2026
DA  - 2026/10/26
TI  - Advances in Plant Electrical Signals for Plant Health Monitoring and Smart Agriculture
JO  - Journal of Plant Electrobiology
T2  - Journal of Plant Electrobiology
JF  - Journal of Plant Electrobiology
VL  - 2
IS  - 1
SP  - 1
EP  - 12
DO  - 10.62762/JPE.2026.825022
UR  - https://www.icck.org/article/abs/JPE.2026.825022
KW  - plant electrical signals
KW  - plant electrome
KW  - sensors
KW  - stress identification
KW  - smart agriculture
AB  - Plant electrical signals are fast electrophysiological responses to environmental stimuli, physiological regulation and stress. Because they often change before visible symptoms appear, they are attractive indicators for early plant-health monitoring and for sensing in precision agriculture. Research in this area has moved from recording single action potentials to analyzing the plant electrome, and now draws on flexible wearable electrodes, implantable and electrochemical sensors, machine learning, multi-source data fusion and edge-cloud computing. This review follows the technical chain from mechanism to application. We first summarize the physiological basis of the main signal types and how they relate to biotic and abiotic stress. We then compare acquisition technologies, including conventional electrodes, flexible wearable devices, microneedles and electrochemical sensors for biochemical markers. Next, we discuss preprocessing, multi-scale feature extraction, and recognition with conventional machine learning, deep learning and multi-source fusion. Finally, we examine applications in environmental sensing and stress identification and outline the remaining obstacles to field use. Most published results still come from laboratory or greenhouse studies with small datasets and non-standard protocols. Progress toward field deployment will depend on standardized acquisition and reporting, long-term sensor stability, cross-species and cross-site validation, open datasets, interpretable models and low-power edge inference. With these elements in place, plant electrical signals could serve as one component of decision-support systems for early warning and crop management.
SN  - 3071-6268
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Zhang2026Advances,
  author = {Xiaohui Zhang and Yingkai Fu and Chi Zhang and Jian Yang and Zeyu Zhai},
  title = {Advances in Plant Electrical Signals for Plant Health Monitoring and Smart Agriculture},
  journal = {Journal of Plant Electrobiology},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {1-12},
  doi = {10.62762/JPE.2026.825022},
  url = {https://www.icck.org/article/abs/JPE.2026.825022},
  abstract = {Plant electrical signals are fast electrophysiological responses to environmental stimuli, physiological regulation and stress. Because they often change before visible symptoms appear, they are attractive indicators for early plant-health monitoring and for sensing in precision agriculture. Research in this area has moved from recording single action potentials to analyzing the plant electrome, and now draws on flexible wearable electrodes, implantable and electrochemical sensors, machine learning, multi-source data fusion and edge-cloud computing. This review follows the technical chain from mechanism to application. We first summarize the physiological basis of the main signal types and how they relate to biotic and abiotic stress. We then compare acquisition technologies, including conventional electrodes, flexible wearable devices, microneedles and electrochemical sensors for biochemical markers. Next, we discuss preprocessing, multi-scale feature extraction, and recognition with conventional machine learning, deep learning and multi-source fusion. Finally, we examine applications in environmental sensing and stress identification and outline the remaining obstacles to field use. Most published results still come from laboratory or greenhouse studies with small datasets and non-standard protocols. Progress toward field deployment will depend on standardized acquisition and reporting, long-term sensor stability, cross-species and cross-site validation, open datasets, interpretable models and low-power edge inference. With these elements in place, plant electrical signals could serve as one component of decision-support systems for early warning and crop management.},
  keywords = {plant electrical signals, plant electrome, sensors, stress identification, smart agriculture},
  issn = {3071-6268},
  publisher = {Institute of Central Computation and Knowledge}
}