Kanneh et al. (2026) Utilising the Potential of a Robust Three-Band Hyperspectral Vegetation Index for Monitoring Plant Moisture Content in a Summer Maize-Winter Wheat Crop Rotation Farming System

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

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-01-14
• Authors: James E. Kanneh, C. H. Li, Yaoming Ma, S Li, Madjebi Collela Be, Zuji Wang, Deyu Zhong, Zhiguo Han, Hao Li, Jinglei Wang
• DOI: 10.3390/rs18020271

Research Groups

Not specified in the provided text.

Short Summary

This study developed new tri-band spectral vegetation indices to enhance the accuracy of monitoring plant moisture content (PMC) in summer maize and winter wheat, finding that the Normalised Water Stress Index (NWSI) combined with machine learning models significantly improved PMC estimation.

Objective

• To develop new tri-band spectral vegetation indices that enhance the accuracy of monitoring plant moisture content (PMC) in summer maize (SM) and winter wheat (WW).

Study Configuration

• Spatial Scale: Field-scale experimental plots for summer maize and winter wheat.
• Temporal Scale: Growing seasons of summer maize and winter wheat, involving rotations and irrigation treatments.

Methodology and Data

• Models used:
  • Tri-band hyperspectral vegetation indices: Normalised Water Stress Index (NWSI), Normalised Difference Index (NDI), Exponential Water Stress Index (EWSI).
  • Machine learning models: Random Forest (RF), Partial Least Squares Regression (PLSR), Support Vector Machine (SVM), Artificial Neural Network (ANN).
• Data sources:
  • Field spectroradiometer measurements of canopy reflectance.
  • Plant moisture content (PMC) data from summer maize and winter wheat under various irrigation treatments (W0, W1, W2, W3, W4).

Main Results

• The Normalised Water Stress Index (NWSI) consistently outperformed other developed and traditional indices for assessing plant moisture content (PMC).
• NWSI showed strong negative correlations with PMC: R = -0.8369 for maize and R = -0.9313 for wheat.
• Among index-type models, NWSI-PLSR exhibited the best performance with an R² of 0.7878.
• When new indices were combined with traditional indices, the NWSI-Published indices-SVM model achieved superior performance with an R² of 0.8203.
• The Random Forest (RF) model demonstrated the most consistent performance and achieved the highest average R² across all input types.
• NDI-Published indices models also outperformed models using only published indices.

Contributions

• Development and validation of novel tri-band spectral vegetation indices (NWSI, NDI, EWSI) specifically designed for monitoring plant moisture content in summer maize and winter wheat.
• Demonstration of significantly improved accuracy in PMC monitoring by combining these new indices with mainstream machine learning models compared to traditional methods.
• Provides a technical basis and support for precision irrigation strategies, offering significant potential for practical application in sustainable farming.

Funding

Not specified in the provided text.

Citation

@article{Kanneh2026Utilising,
  author = {Kanneh, James E. and Li, C. H. and Ma, Yaoming and Li, S and Be, Madjebi Collela and Wang, Zuji and Zhong, Deyu and Han, Zhiguo and Li, Hao and Wang, Jinglei},
  title = {Utilising the Potential of a Robust Three-Band Hyperspectral Vegetation Index for Monitoring Plant Moisture Content in a Summer Maize-Winter Wheat Crop Rotation Farming System},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18020271},
  url = {https://doi.org/10.3390/rs18020271}
}