Li et al. (2026) Quantifying and Communicating Uncertainty in SAR-Based Flood Mapping via Density-Aware Neural Networks and Conformal Risk Control

Identification

• Journal: IEEE Transactions on Geoscience and Remote Sensing
• Year: 2026
• Date: 2026-01-01
• Authors: Yu Li, Patrick Matgen, Marco Chini
• DOI: 10.1109/tgrs.2026.3661208

Research Groups

[No information provided in the paper text.]

Short Summary

This paper focuses on quantifying and communicating uncertainty in flood mapping derived from Synthetic Aperture Radar (SAR) data, employing density-aware neural networks and conformal risk control.

Objective

• To quantify uncertainty in SAR-based flood mapping.
• To develop methods for effectively communicating this uncertainty.
• To utilize density-aware neural networks and conformal risk control as key methodologies for achieving these objectives.

Study Configuration

• Spatial Scale: [No information provided in the paper text.]
• Temporal Scale: [No information provided in the paper text.]

Methodology and Data

• Models used: Density-Aware Neural Networks, Conformal Risk Control.
• Data sources: Synthetic Aperture Radar (SAR) data.

Main Results

[No information provided in the paper text.]

Contributions

[No information provided in the paper text.]

Funding

[No information provided in the paper text.]

Citation

@article{Li2026Quantifying,
  author = {Li, Yu and Matgen, Patrick and Chini, Marco},
  title = {Quantifying and Communicating Uncertainty in SAR-Based Flood Mapping via Density-Aware Neural Networks and Conformal Risk Control},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2026},
  doi = {10.1109/tgrs.2026.3661208},
  url = {https://doi.org/10.1109/tgrs.2026.3661208}
}