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.

Automated vehicles (AVs) provide several advantages in solving issues of road traffic; including enhanced safety, reduced greenhouse gas emissions, and reduced traffic congestion. As AVs are still relatively new developments in developing countries, AV adoption faces challenges from both technological and psychological issues. Therefore, our initial research focus is on identifying the factors that influence the intention to use conditionally automated vehicles (CAVs; SAE Level 3). An extended technology acceptance model (TAM), which includes Trust, Perceived Risks, and Environmental concerns, is proposed as the predictor model in this study. The 299 participants gathered through online surveys in Thailand were examined using the Structural Equation Model (SEM) technique. In this study, Trust was shown to be the strongest predictor of Intention, followed by Perceived Ease of Use, whereas Perceived Usefulness had no impact on intention to use the SAE Level 3. The results of this study will be able to guide the forming of future policies that aim at promoting the use of AVs and helping technology developers create systems to better meet the needs of users in developing nations.

Globally, road traffic collisions cause over a million deaths annually, with pedestrians accounting for 23%. In developing countries, most pedestrian deaths occur on urban arterial roads, particularly at midblock crossings. This study analyzes the factors influencing driver yielding behavior at midblock crosswalks on urban arterial roads in Thailand. This study analyzed the factors influencing driver yielding behavior at the midblock crosswalk before and after the upgrade from a zebra crossing (C1) to a smart pedestrian crossing (C2), which is a smart traffic signal detecting and controlling pedestrians and vehicles entering the crosswalk. Video-based observations were used to assess driver yielding behavior, with multinomial logistic regression applied to develop driver yielding behavior models. The results revealed that the chances of a driver yielding at C2 were higher than at C1, and the yielding rate increased by 74%. The models indicate that the number and width of traffic lanes, width and length of crosswalks, vulnerable group, number of pedestrians, pedestrian crossing time, number of vehicles, vehicle speed, headway, post-encroachment time between a vehicle and pedestrian, and roadside parking are the significant factors influencing yielding behavior. These findings propose measures to set proper crosswalk improvements (e.g., curb extensions), speed reduction measures, enforcement (e.g., parking restrictions), public awareness campaigns, and education initiatives.

The challenges resulting from rapid economic growth, urbanization, and increased motorization in developing nations necessitate a comprehensive and sustainable approach to urban public transport planning. While sustainable urban public transport (SUPT) planning offers a solution, the complexity of choosing suitable policy measure options remains a challenge. This study first introduces a decision support framework (DSF) that integrates the sustainable urban public transport manual (SUPTM) adopted for generating the potential SUPT policy measure options, the KonSULT knowledge base applied for providing the performance scores of each measure option for all determined criteria, and the HMADM (including FAHP, FSM, and TOPSIS) technique to create, rank, and select SUPT policy measure options tailored to medium-sized urban areas in developing nations. A case study of Khon Kaen City, Thailand, illustrates the practical application of the framework, resulting in a set of 31 (91.2%) out of the total of 34 ranked policy measure options. Comparing these prioritizations with the city’s existing plan reveals a substantial agreement, which suggests the potential applicability of the DSF. Overall, the DSF marks a significant advancement in SUPT planning, which is crucial for shaping efficient, equitable, and environmentally conscious urban mobility in developing countries, which are undergoing transformative change.

Globally, road traffic collisions cause over a million deaths annually, with pedestrians accounting for nearly one-quarter (23%) of these fatalities. This casualty proportion highlights the critical importance of adhering to traffic regulations. This study analyzes the factors influencing driver yielding behavior at midblock crosswalk improvements, comparing (1) a typical zebra crossing (C1) and (2) an intelligent signalized crosswalk (C2). The study used video-based observational data to investigate driver behaviors and factors influencing driver behaviors. The study applied multinomial logistic regression to formulate yielding behavior models. The results indicate that the number of traffic lanes, width of the traffic lanes, width and length of the crosswalk, vulnerable group, the number of pedestrian crossings, pedestrian crossing time, the number of vehicles approaching a crosswalk, speed of vehicle, headway, the post-encroachment time (PET) between vehicles and pedestrian, and roadside parking are the significant factors influence yielding behavior. These findings provide a better understanding of the factors influencing driver yielding behavior and propose measures to set proper physical improvements (e.g., curb extensions, raised pedestrian platforms, and pedestrian fencing), enforcement (e.g., parking restriction, speed violation detection), public awareness campaigns, and education initiatives.