Zhu et al. (2025) A Multi-Sensor Fusion Approach for the Assessment of Water Stress in Woody Plants

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Forests
• Year: 2025
• Date: 2025-11-27
• Authors: Jun Zhu, Sijun Qin, Wenbo Liu, Qiang Fu, Yin Wu
• DOI: 10.3390/f16121785

Research Groups

Not explicitly provided in the given text.

Short Summary

This study developed an indoor multi-sensor phenotyping platform and a novel hybrid machine learning model to accurately and early diagnose plant water stress, achieving high classification accuracy for Perilla frutescens.

Objective

• To develop a comprehensive multi-sensor platform and a robust analytical model for accurate and early diagnosis of plant water status, thereby advancing climate-smart forestry and early warning systems.

Study Configuration

• Spatial Scale: Individual plant level (e.g., Perilla frutescens).
• Temporal Scale: Not explicitly defined, but implies dynamic monitoring over time for early diagnosis.

Methodology and Data

• Models used: Whale Optimization Algorithm-based Multi-Kernel Extreme Learning Machine (WOA-MK-ELM) for classification.
• Data sources: Coordinated high-throughput data acquisition from a hyperspectral camera, a thermal infrared imager, and a LiDAR scanner integrated into a three-axis mobile truss system.

Main Results

• The proposed framework achieved high accuracy in classifying water stress degrees in Perilla frutescens.
• Specific performance metrics include an accuracy of 93.03%, an average precision of 93.11%, an average recall of 94.04%, and an F1-score of 0.94.
• The framework provides a powerful prototype and a robust analytical approach for smart forestry and early warning systems.

Contributions

• Development of an indoor multi-sensor phenotyping platform integrating hyperspectral, thermal infrared, and LiDAR data for coordinated high-throughput plant monitoring.
• Introduction of a novel hybrid model, WOA-MK-ELM, which enhances classification robustness by adaptively fusing multi-modal features within a dual Gaussian kernel space.
• Demonstration of high prediction accuracy for early water stress diagnosis, offering a significant advancement for climate-smart forestry and early warning systems.

Funding

Not explicitly provided in the given text.

Citation

@article{Zhu2025MultiSensor,
  author = {Zhu, Jun and Qin, Sijun and Liu, Wenbo and Fu, Qiang and Wu, Yin},
  title = {A Multi-Sensor Fusion Approach for the Assessment of Water Stress in Woody Plants},
  journal = {Forests},
  year = {2025},
  doi = {10.3390/f16121785},
  url = {https://doi.org/10.3390/f16121785}
}