Predicting urban flooding susceptibility of public transit systems using machine learning approaches: a case study of the largest city in Canada

Urban floods often cause the functional disruption of public transit systems, thereby impeding people's mobility and resulting in adverse socio-economic consequences. Climate change, rapid urbanization, and unplanned disaster management further increase trends of urban floods with higher frequency and intensity. This study employs data-driven machine learning (ML) models for predicting the flooding susceptibility of public transit systems in Toronto, ON, Canada. Four ML approaches are employed to evaluate the future risks of public transit systems being inundated by flooding events: 1) Random Forest (RF); 2) eXtreme Gradient Boosting (XGBoost); 3) K Nearest Neighbor (KNN); and 4) Naïve Bayes (NB). We estimate flooding probability based on the relationship between flood inundation events and their contributing factors. Flood-plain maps by Toronto and Region Conservation Authority (TRCA) are used to generate flood and non-flood locations as a basis for training (70% of samples) and validating (30% of samples) ML models. We use the Area-Under Receiver Operating Characteristic (AUROC) curve to evaluate the prediction results of ML models. All four models show a high level of accuracy higher than 95%. Our results demonstrate public transit systems near major river channels are highly susceptible to floods which corroborated with historical flooding incidents in 2013 and 2018. The outcome of the study can be helpful to enhance the resilience of public transit systems in the city of Toronto and can facilitate evidence-based planning and policy to make cities more sustainable, livable, and resilient against flood hazards.