Saha et al. (2026) Plant acoustic emission as early stress signals: Towards remote integrated monitoring for sustainable agriculture

Identification

• Journal: European Journal of Agronomy
• Year: 2026
• Date: 2026-03-26
• Authors: Bedabrata Saha, Anshu Rastogi
• DOI: 10.1016/j.eja.2026.128100

Research Groups

• Department of Bioclimatology, Faculty of Environmental and Mechanical Engineering, Poznan University of Life Sciences, Poland

Short Summary

This review synthesizes current understanding of plant acoustic emissions (AEs) as early, non-invasive indicators of abiotic stress in crops, particularly hydraulic dysfunction. It proposes an integrated monitoring framework combining ground-based AE sensors with remote sensing data and machine learning to enable proactive precision agriculture.

Objective

• To elucidate the dual role of plant acoustics in perception and emission, highlighting acoustic emissions (AEs) as early indicators of hydraulic dysfunction in crops.
• To propose a synergistic integration of ground-based AE monitoring with remote sensing technologies and machine learning for sustainable, physiology-informed crop monitoring and intelligent decision systems in agriculture.

Study Configuration

• Spatial Scale: From individual plants (point-specific AE monitoring) to field and regional scales (via integration with satellite/UAV data).
• Temporal Scale: Continuous, high-frequency monitoring for early stress detection, preceding visible symptoms.

Methodology and Data

• Models used: Machine learning, crop digital twin driven fusion.
• Data sources: Plant acoustic emissions (AEs) from Internet of Things (IoT) enabled sensors, satellite-derived spectral, thermal, and radar data, unmanned aerial vehicle (UAV)-derived spectral, thermal, and radar data.

Main Results

• Plants actively perceive and emit acoustic signals, with ultrasonic acoustic emissions (AEs) generated during physiological disruptions like xylem cavitation under osmotic stress.
• AEs serve as sensitive, non-invasive biomarkers for hydraulic dysfunction and other abiotic stresses in crops, preceding metabolic or structural damage.
• A proposed integrated framework combines point-specific, real-time AE data from IoT sensors with spatially extensive remote sensing data (spectral, thermal, radar) from satellites and UAVs.
• Machine learning and crop digital twin driven fusion enhances spatial resolution, improves stress classification accuracy, and boosts predictive capabilities, while mitigating limitations of optical indices like atmospheric interference.
• This framework enables proactive precision agriculture, facilitating early triggering of deficit irrigation, optimizing irrigation scheduling, and improving nutrient and pest management for climate-resilient farming.

Contributions

• First-time elucidation of the importance of plant acoustic emissions (AEs) and their applications in agronomy, specifically as early indicators of hydraulic dysfunction in crops.
• Proposal of a novel synergistic integration framework combining ground-based AE monitoring with remote sensing technologies (satellite/UAV) and machine learning for enhanced, scalable crop stress detection.
• Introduction of a pathway for sustainable, physiology-informed crop monitoring and intelligent decision systems through bioacoustics and spectral synergy.

Funding

• Not specified in the provided text.

Citation

@article{Saha2026Plant,
  author = {Saha, Bedabrata and Rastogi, Anshu},
  title = {Plant acoustic emission as early stress signals: Towards remote integrated monitoring for sustainable agriculture},
  journal = {European Journal of Agronomy},
  year = {2026},
  doi = {10.1016/j.eja.2026.128100},
  url = {https://doi.org/10.1016/j.eja.2026.128100}
}