Beyrouthy et al. (2026) Bridging Temporal Gaps in Thermal Remote Sensing: A Generative Adversarial Network Approach to Land-Cover-Stratified Diurnal Heat Retention in Peri-Urban Landscapes

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

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-21
• Authors: Naji El Beyrouthy, Mario J. Al Sayah, Rita Der Sarkissian, Rachid Nedjaï
• DOI: 10.3390/rs18183259

Research Groups

• Laboratoire d'Études en Géophysique et Océanographie Spatiale (LEGOS), France
• Centre National de la Recherche Scientifique (CNRS), France
• University of Paris, France

Short Summary

This study introduces the Relative Diurnal Thermal Index (RDTI) to quantify urban heat island effects at field scale, providing a dimensionless and land-cover-stratified anomaly that expresses diurnal temperature range as a standardized anomaly against historical climatology.

Objective

• Investigate the feasibility of using machine learning techniques to generate high-resolution land surface temperatures for urban areas and develop a new indicator to quantify urban heat island effects at field scale.

Study Configuration

• Spatial Scale: Four temperate French metropolitan peripheries (Paris, Lille, Nantes, and Bordeaux) with a spatial resolution of 10 m.
• Temporal Scale: Daily time series from 2000 to 2025.

Methodology and Data

• Models used: Conditional Generative Adversarial Network (cGAN)
• Data sources: MODIS day/night land surface temperature, Landsat-8/9 and Sentinel-2 imagery

Main Results

• The Relative Diurnal Thermal Index (RDTI) is a dimensionless indicator that expresses diurnal temperature range as a standardized anomaly against historical climatology.
• Built-up surfaces showed suppressed nocturnal cooling relative to cropland in all four cities, with Cohen’s d values ranging from 0.54 to 1.67.

Contributions

• The RDTI provides a field-scale, climatologically grounded diurnal complement to existing urban heat island indicators.
• This study demonstrates the potential of machine learning techniques for generating high-resolution land surface temperatures and developing new indicators for urban climate research.

Funding

• This research was funded by the French National Research Agency (ANR) under grant number [ANR-19-CE01-0001].

Citation

@article{Beyrouthy2026Bridging,
  author = {Beyrouthy, Naji El and Sayah, Mario J. Al and Sarkissian, Rita Der and Nedjaï, Rachid},
  title = {Bridging Temporal Gaps in Thermal Remote Sensing: A Generative Adversarial Network Approach to Land-Cover-Stratified Diurnal Heat Retention in Peri-Urban Landscapes},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18183259},
  url = {https://doi.org/10.3390/rs18183259}
}