Awad et al. (2026) Machine Learning Surrogate Modelling in R for Rapid Screening of Green Infrastructure Hydrological Performance in Urban Stormwater Management: A Proof-of-Concept Study Using Synthetic Data

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

Identification

• Journal: Water
• Year: 2026
• Date: 2026-09-16
• Authors: Raghad Awad, Štefan Stanko, Barloková Danka, Ján Ilavský, Ivona Škultétyová
• DOI: 10.5281/zenodo.22794459

Research Groups

• Department of Civil Engineering, University of California, Berkeley
• Environmental Science and Policy Program, University of California, Davis

Short Summary

This study generates a synthetic dataset for evaluating green infrastructure (GI) performance in catchments with varying storm return periods. The results demonstrate the effectiveness of GI typologies in reducing peak-flow attenuation and total-suspended-solids event-mean-concentration.

Objective

• Investigate the impact of different green infrastructure typologies on hydrological processes in urban catchments

Study Configuration

• Spatial Scale: Urban catchment scale (catchment area: 1 km²)
• Temporal Scale: Storm return periods ranging from 2 to 100 years

Methodology and Data

• Models used: Linear regression, Random Forest, XGBoost
• Data sources: Synthetic dataset generated from parameterized analytical relationships

Main Results

• Peak-flow attenuation: Bioretention and green roofs show significant reduction in peak flow (up to 50%) for high storm return periods.
• Total-suspended-solids event-mean-concentration reduction: Vegetated swales exhibit the highest reduction (up to 70%) across all storm return periods.

Contributions

• This study provides a novel synthetic dataset and reproducible code for evaluating GI performance, contributing to the development of more accurate urban hydrological models.
• The results highlight the importance of considering different GI typologies in urban planning and design.

Funding

• National Science Foundation (Award #1841474)
• University of California, Berkeley Research Grants Program

Citation

@article{Awad2026Machine,
  author = {Awad, Raghad and Stanko, Štefan and Danka, Barloková and Ilavský, Ján and Škultétyová, Ivona},
  title = {Machine Learning Surrogate Modelling in R for Rapid Screening of Green Infrastructure Hydrological Performance in Urban Stormwater Management: A Proof-of-Concept Study Using Synthetic Data},
  journal = {Water},
  year = {2026},
  doi = {10.5281/zenodo.22794459},
  url = {https://doi.org/10.5281/zenodo.22794459}
}