Application of Machine Learning for Integrated Flood Risk Assessment: Case Study of Hurricane Harvey in Houston, Texas

Flood risk, encompassing hazard, exposure, and vulnerability represents major potential losses to society. Multi-variable flood risk models can assist researchers and practitioners in more accurate flood loss analyses. However, such models comprise complexities associated with data and variables. Machine learning techniques that address such complexities and non-linear relationships have primarily focused on flood hazard prediction rather than comprehensive risk assessment and damage estimations. Therefore, there is a need to combine risk elements using such methods. To address this need, this study utilized the Machine Learning Random Forest algorithm to analyze the correlations between the physical flood damage caused by Hurricane Harvey in 2017 in Houston, Texas and hazard, exposure, and vulnerability-related variables. This approach offers a clearer understanding of how different risk elements interact to influence damage outcomes, particularly in highly urbanized environments. The methodology provides a robust framework for analyzing non-linear correlations and the combined impact of these variables on flood risk. We also explored the reasons for the unexpectedly low importance of social vulnerability factors in our results compared to the environmental justice concept. These findings and conclusions can provide insights to planners and stakeholders enhancing their understanding of the underlying causes contributing to flood risk. Future research can expand upon this study’s methodology and findings by incorporating additional factors related to climate change.