Riverine flooding in Southeast Asian cities increasingly affects their residents, often causing prolonged negative consequences due to their geographic position in lowland areas. The rapid expansion of urban areas into highly vulnerable zones has only exacerbated this issue. To mitigate flood risk, it is crucial to assess and map flood susceptibility and for incorporation into future urban planning. This study evaluates and compares the predictive performance of logistic regression (LR) and the autoencoder multilayer perceptron (AE-MLP), an advanced model, for urban flood risk assessment in Ubon Ratchathani, Thailand. The models were assessed using an area under the receiver operating characteristic curve (AUC) and several indexes (accuracy, F1-score, precision, Recall). This study also mapped vulnerable populations based on estimated flood risk from each model. The AE-MLP model outperformed the LR model, achieving an AUC of 0.950 compared to 0.860. An analysis of flood risk distribution revealed that the LR model estimated 1.79% of the population residing in high-risk areas and 0.83% in very high-risk areas. In comparison, the AE-MLP model estimated 24.00 and 7.97%, respectively, demonstrating its superior sensitivity in identifying vulnerable zones. These findings indicate that the AE-MLP model can significantly improve flood risk prediction and accurately identify high-risk areas. Integrating these models into urban planning and disaster management frameworks can enhance resilience to flooding.

Urban floods frequently occur in Southeast Asian cities, causing extensive road disruptions and a significant decline in overall urban mobility. To effectively adapt to such conditions, it is crucial to understand how residents modify their travel behavior and daily activities during flood events. This study investigates these behavioral changes by comparing individual travel behaviors and activities under normal and flooding conditions, based on an Activity Diary Survey conducted in Kudus, Indonesia. The comparative analysis reveals that during floods, individuals tend to reduce non-essential activities and limit travel to essential purposes such as work and education. The findings from chi-square tests and applying the RF (random forest) model indicate that socioeconomic characteristics—particularly age, license, income, and level of flood—significantly influence the likelihood of behavioral change. These results highlight that flood-induced disruptions in mobility are not only physical but also socially differentiated, reflecting disparities in vulnerability and adaptive capacity.

Riverine floods are a recurring and increasingly severe problem in Southeast Asia, often resulting in the submersion of large urban areas for extended periods. As a result, urban mobility is severely disrupted, significantly affecting the daily activities of residents. Integrating behavioral changes during floods into travel demand forecasting is essential for assessing flood adaptation measures in the transportation sector. However, no detailed analysis has been conducted on the impacts of urban flooding on daily activities and travel behavior, and no examples are available on how to incorporate these impacts into travel demand forecasts. This study proposes the development of an activity-based traffic demand forecasting model that explicitly incorporates behavioral changes in individual activity patterns during floods. The model is designed to reflect the disruptions caused by riverine floods and their impact on daily travel behaviors, road closures, and reduced accessibility, which are often overlooked in traditional forecasting methods. Then, the model evaluates adaptation measures in the transportation sector (such as the elevation of arterial roads), supporting strategic planning for resilient urban mobility during floods.