Exploring interactive and nonlinear effects of key factors on intercity travel mode choice using XGBoost

Effects of the built environment on travel distance in bus-oriented, medium-sized cities in China

The impact of the built environment and weather conditions on travel behavior has been widely studied. However, limited studies have focused on better understanding such effects in medium-sized cities with bus-oriented transit systems, particularly from a separate perspective of travelers’ origins and destinations. We took Weinan, China, as a representative of second-tier cities in developing countries that concentrate on bus-oriented development strategies. New evidence of feature importance and nonlinear effects of crucial factors were revealed by an interpretable machine learning-based approach combining XGBoost and Shapley Additive Explanation (SHAP) with multi-source data. Most key factors were critical at both origins and destinations, such as the density of residential and commercial facilities. However, several important factors, such as road density and boarding time, had strong imbalanced effects on travel behavior. These findings provide novel insights and empirical implications to support urban planning strategies in medium-sized cities.

Determinants of passengers' ticketing channel choice in rail transit systems: New evidence of e-payment behaviors from Xi'an, China

What Affects Bus Passengers’ Travel Time? A View from the Built Environment and Weather Condition

The study aims to examine the impact of the built environment and weather conditions on travel time for bus passengers in Weinan, China. Various sources of data, including smart card data, bus GPS data, bus station data, road information data, and smart card swiping time, were integrated and analyzed. The study employed the light gradient boosting machine (LightGBM) model and SHapley Additive exPlanations (SHAP) value to assess the feature importance and nonlinear effects of different types of POI density, weather conditions, and time series on bus passengers’ travel time. The study findings indicate that several factors are associated with bus passengers’ travel time, including destination residential density, destination diversity, destination life service density, origin science and education density, origin residential density, origin diversity, humidity, visibility, boarding time between 7 and 8 a.m., and precipitation. This study also reveals nonlinear threshold effects. The study findings provide valuable insights that can be utilized to optimize the bus network and develop low-carbon-oriented land-use planning.

Determinants of passengers' ticketing channel choice in rail transit systems: New evidence of e-payment behaviors from Xi'an, China

基于极端随机树的城际公路客流影响机理研究, 2023世界交通运输大会(WTC2023), 武汉, 中国, 2023.6.14-6.17.

Emotional wellbeing in intercity travel: Factors affecting passengers' long-distance travel moods

The travel mood perception can significantly affect passengers' mental health and their overall emotional wellbeing when taking transport services, especially in long-distance intercity travels. To explore the key factors influencing intercity travel moods, a field survey was conducted in Xi'an to collect passengers' individual habits, travel characteristics, moods, and weather conditions. Travel mood was defined using the 5-Likert scale, based on degrees of happiness, panic, anxiety, and tiredness. A support vector machine (SVM) and ordered logit model were used in tandem for determinant identification and exploring their respective influences on travel moods. The results showed that gender, age, occupation, personal monthly income, car ownership, external temperature, precipitation, relative humidity, air quality index, visibility, travel purposes, intercity travel mode, and intercity travel time were all salient influential variables. Specifically, intercity travel mode ranked the first in affecting panic and anxiety (38 and 39% importance, respectively); whereas occupation was the most important factor affecting happiness (23% importance). Moreover, temperature appeared as the most important influencing factor of tiredness (22% importance). These findings help better understand the emotional health of passengers in long-distance travel in China.