Domínguez et al. (2026) Flood Detection Benchmark

Identification

• Journal: Mendeley Data
• Year: 2026
• Date: 2026-06-03
• Authors: Carlos Rodríguez Domínguez, Manuel Pedro Rodríguez Bolívar, Laura Alcaide Muñoz
• DOI: 10.17632/m5kf9sv2rs.1

Research Groups

• Universidad de Granada, Andalusia, Granada

Short Summary

This study benchmarks machine learning (ML) and agent-based implementations of flood detection mechanisms to identify the most efficient approach regarding cost, prediction time, and user outputs.

Objective

• To compare different implementations of flood detection (ML vs. agent-based) to determine the optimal balance between operational cost, prediction speed, and the quality of outputs for final users.

Study Configuration

• Spatial Scale: Not specified
• Temporal Scale: Not specified

Methodology and Data

• Models used: Machine Learning (ML) and Agent-Based Technology
• Data sources: Not specified

Main Results

• The research provides a benchmark analysis comparing ML and agent-based systems, specifically evaluating metrics such as reduced cost, prediction time, and the utility of outputs for emergency response and flood risk management.

Contributions

• Establishes a comparative framework for flood detection technologies, offering guidance on whether ML or agent-based systems are more effective for real-time emergency response and risk management.

Funding

• EIT Food (European Institute of Innovation and Technology Leuven), Grant ID: DIGIMPACT.EU

Citation

@article{Domínguez2026Flood,
  author = {Domínguez, Carlos Rodríguez and Bolívar, Manuel Pedro Rodríguez and Muñoz, Laura Alcaide},
  title = {Flood Detection Benchmark},
  journal = {Mendeley Data},
  year = {2026},
  doi = {10.17632/m5kf9sv2rs.1},
  url = {https://doi.org/10.17632/m5kf9sv2rs.1}
}