Harandi et al. (2026) Multi-Sensor Mapping of Aquatic Vegetation Using Sentinel-2, SAR–Optical Fusion and Derived Spectral and SAR Indices in South Florida

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

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-09
• Authors: Bella Harandi, Nathan M. Gavin, Jing Hu, Weiwei Zhan
• DOI: 10.3390/rs18183086

Research Groups

• University of Florida's Department of Civil and Coastal Engineering
• University of Miami's Rosenstiel School of Marine and Atmospheric Science

Short Summary

This study develops a multi-sensor framework for mapping submerged aquatic vegetation (SAV) and emergent aquatic vegetation (EAV) in the Everglades, achieving high accuracy through the combination of Sentinel-1 SAR, Sentinel-2 optical imagery, and derived spectral and SAR indices.

Objective

• Investigate the effectiveness of multi-sensor data fusion for accurate mapping of SAV and EAV in dynamic environments like the Everglades stormwater treatment areas (STAs).

Study Configuration

• Spatial Scale: Local to regional scale, focusing on the Everglades STAs in South Florida.
• Temporal Scale: The study likely spans a period of time to account for seasonal changes and hydrological variability.

Methodology and Data

• Models used: Random forest (RF) and TabNet classifiers were employed for aquatic vegetation discrimination.
• Data sources: Sentinel-1 SAR, Sentinel-2 optical imagery, and derived spectral and SAR indices were utilized in the study.

Main Results

• The combination of Sentinel-1, Sentinel-2, and derived spectral and SAR indices achieved the most robust performance (OA = 0.86–0.90) for both TabNet classifiers.
• Spatial generalization was improved with this configuration, particularly in unseen validation areas.

Contributions

• This study contributes to the development of scalable wetland vegetation monitoring methods, especially in cloud-prone and hydrologically dynamic environments like the Everglades.
• The findings highlight the potential benefits of multi-sensor data fusion for accurate mapping of SAV and EAV.

Funding

• This research was supported by [insert project/program name(s) and reference codes].

Citation

@article{Harandi2026MultiSensor,
  author = {Harandi, Bella and Gavin, Nathan M. and Hu, Jing and Zhan, Weiwei},
  title = {Multi-Sensor Mapping of Aquatic Vegetation Using Sentinel-2, SAR–Optical Fusion and Derived Spectral and SAR Indices in South Florida},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18183086},
  url = {https://doi.org/10.3390/rs18183086}
}