Urban Flood Risk Prediction: A Machine Learning, Approach Based on Green Infrastructure for Sustainable Cities

DOI

10.2991/978-94-6239-682-1_18How to use a DOI?

Keywords

Sustainable Cities; Green Infrastructure; Flood Risk Prediction; Machine Learning; Natural Disasters

Abstract

In light of rapid urbanization and climate change, cities are becoming more and more susceptible to flooding. This study proposes one of the few machine learning approaches incorporating green infrastructure, such as parks and permeable pavement, into how cities adapt to flooding disasters. Using historical flood data and Random Forest and XGBoost models, synthetic data was generated to estimate the probability of flooding based on rainfall, soil moisture, and impervious surface cover. The models produced AUC scores of greater than 0.99, indicating that flood risk is reduced by 14% if green infrastructure is added. The impacts of the flooded features were confirmed in the ablation studies, and sensitivity analysis demonstrates that while meteorological factors like rainfall dominate the baseline risk, changes in the coverage of green features pro-vide the most significant mitigating effect among actionable urban variables. This is beneficial to urban planners and promotes sustainable development. Future work should focus on the use of real-time data, which will help planners adapt cities more quickly to predicted flood disasters.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ji Zhang
AU  - Jinyong Wang
AU  - Ho Ming Kang
AU  - Xiaona Li
AU  - Shengming Luo
AU  - Bei Xu
AU  - Yadong Niu
AU  - Luning Qian
PY  - 2026
DA  - 2026/06/30
TI  - Urban Flood Risk Prediction: A Machine Learning, Approach Based on Green Infrastructure for Sustainable Cities
BT  - Proceedings of the 2025 7th International Conference on Civil Architecture and Urban Engineering (ICCAUE 2025)
PB  - Atlantis Press
SP  - 175
EP  - 186
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-682-1_18
DO  - 10.2991/978-94-6239-682-1_18
ID  - Zhang2026
ER  -