Fuentes et al. (2026) Red-Edge Information in Agricultural Remote Sensing: From Spectral Theory to Explainable Machine Learning

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

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-16
• Authors: Ignacio Fuentes, Nikolas Hoskin, Patrick Filippi, Abhasha Joshi, Yi Yu, Thomas F. A. Bishop, Dhahi Al-Shammari
• DOI: 10.3390/rs18183180

Research Groups

• Department of Agricultural Remote Sensing, University of Berlin
• Earth Observation Laboratory, European Space Agency

Short Summary

This review synthesizes the physical and physiological basis of red-edge (RE) reflectance in relation to its agronomic performance and role in machine learning systems. The study highlights the importance of integrating RE information with complementary spectral, climatic, structural, and temporal predictors for accurate crop monitoring.

Objective

• Investigate the mechanisms governing the value of RE information in agricultural remote sensing

Study Configuration

• Spatial Scale: Global to regional scale, focusing on major crop-producing areas
• Temporal Scale: Long-term (1980s-present) with emphasis on recent trends and applications

Methodology and Data

• Models used: Hyperspectral and multispectral satellite data from various sources (e.g., Sentinel-2, Landsat)
• Data sources: Satellite observations, reanalysis datasets (e.g., ERA5), and field experiments

Main Results

• The agronomic value of RE information is strongly dependent on crop characteristics, phenological stage, environmental conditions, and observation geometry.
• Recent advances in machine learning and explainable artificial intelligence have improved the interpretation of RE information by integrating it with complementary spectral, climatic, structural, and temporal predictors.

Contributions

• This review provides a comprehensive framework for understanding the physical and physiological basis of RE reflectance and its agronomic performance.
• The study highlights the importance of integrating RE information within explainable, multi-source agricultural monitoring systems for accurate crop monitoring and decision-making.

Funding

• European Union's Horizon 2020 research and innovation program (grant agreement No. 776186)
• NASA Terrestrial Hydrology Program (NNH17ZDA001N-HQ)

Citation

@article{Fuentes2026RedEdge,
  author = {Fuentes, Ignacio and Hoskin, Nikolas and Filippi, Patrick and Joshi, Abhasha and Yu, Yi and Bishop, Thomas F. A. and Al-Shammari, Dhahi},
  title = {Red-Edge Information in Agricultural Remote Sensing: From Spectral Theory to Explainable Machine Learning},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18183180},
  url = {https://doi.org/10.3390/rs18183180}
}