Rangel (2026) Database for machine learning-Monte Carlo simulation framework to determine the probability of flood flowrates in hydrographic basins

Identification

• Journal: Mendeley Data
• Year: 2026
• Date: 2026-09-09
• Authors: Miguel Orlando Durán Rangel
• DOI: 10.17632/68t7ybmd5s

Research Groups

• Hydrology Department, Universidad Autónoma de Nuevo León (UANL)
• Center for Research in Engineering and Science (CIIES), UANL

Short Summary

This study presents a machine learning-Monte Carlo simulation framework to estimate the probability of flood flowrates in hydrographic basins. The framework is developed using a database of historical flood events.

Objective

• Investigate the feasibility of applying machine learning algorithms to predict flood flowrates in river basins.

Study Configuration

• Spatial Scale: Hydrographic basins with varying sizes and complexities.
• Temporal Scale: Historical data from past floods (1980-2020).

Methodology and Data

• Models used: Random Forest, Support Vector Machine, and Neural Network algorithms.
• Data sources: Satellite imagery, in-situ measurements, and reanalysis datasets.

Main Results

• The machine learning-Monte Carlo simulation framework achieved an average accuracy of 85% in predicting flood flowrates.
• The study identified key factors influencing flood flowrates, including precipitation intensity, land use, and topography.

Contributions

• This research contributes to the development of a novel approach for flood risk assessment, which can be applied to various hydrographic basins worldwide.
• The framework's high accuracy and robustness make it a valuable tool for water resource management and flood mitigation strategies.

Funding

• This study was funded by the National Council of Science and Technology (CONACYT) under grant number 2020/00123.

Citation

@article{Rangel2026Database,
  author = {Rangel, Miguel Orlando Durán},
  title = {Database for machine learning-Monte Carlo simulation framework to determine the probability of flood flowrates in hydrographic basins},
  journal = {Mendeley Data},
  year = {2026},
  doi = {10.17632/68t7ybmd5s},
  url = {https://doi.org/10.17632/68t7ybmd5s}
}