Vojtek et al. (2026) Data for: Rapid and high-resolution prediction of fluvial flood inundation using machine learning models trained on hydraulically derived data and river segmentation

Identification

• Journal: Mendeley Data
• Year: 2026
• Date: 2026-01-08
• Authors: Matej Vojtek, Dávid Držík, Jozef Kapusta, Jana Vojteková
• DOI: 10.17632/t3rfrp7fsw.1

Research Groups

Matej Vojtek, Dávid Držík, Jozef Kapusta, Jana Vojteková (Specific institutional affiliations are not provided in the given text.)

Short Summary

This study aims to develop machine learning models for rapid and high-resolution prediction of fluvial flood inundation, leveraging hydraulically derived data and river segmentation for training.

Objective

• To achieve rapid and high-resolution prediction of fluvial flood inundation using machine learning models trained on hydraulically derived data and river segmentation.

Study Configuration

• Spatial Scale: High-resolution (specific units not provided).
• Temporal Scale: Rapid (specific units not provided).

Methodology and Data

• Models used: Machine learning models (specific types not detailed).
• Data sources: Hydraulically derived data, river segmentation data. (Specific raw data sources like satellite, observation, or reanalysis are not mentioned).

Main Results

The provided text is a data description for a scientific paper and does not contain the main results of the study itself.

Contributions

The article contributes a methodology for rapid and high-resolution fluvial flood inundation prediction by integrating machine learning models with hydraulically derived data and river segmentation.

Funding

Funding information is not provided in the given text.

Citation

@article{Vojtek2026Data,
  author = {Vojtek, Matej and Držík, Dávid and Kapusta, Jozef and Vojteková, Jana},
  title = {Data for: Rapid and high-resolution prediction of fluvial flood inundation using machine learning models trained on hydraulically derived data and river segmentation},
  journal = {Mendeley Data},
  year = {2026},
  doi = {10.17632/t3rfrp7fsw.1},
  url = {https://doi.org/10.17632/t3rfrp7fsw.1}
}