Qing-Chang Lu

Dynamic bus travel time prediction models on road with multiple bus routes

Accurate and real-time travel time information for buses can help passengers better plan their trips and minimize waiting times. A dynamic travel time prediction model for buses addressing the cases on road with multiple bus routes is proposed in this paper, based on support vector machines (SVMs) and Kalman filtering-based algorithm. In the proposed model, the well-trained SVM model predicts the baseline bus travel times from the historical bus trip data; the Kalman filtering-based dynamic algorithm can adjust bus travel times with the latest bus operation information and the estimated baseline travel times. The performance of the proposed dynamic model is validated with the real-world data on road with multiple bus routes in Shenzhen, China. The results show that the proposed dynamic model is feasible and applicable for bus travel time prediction and has the best prediction performance among all the five models proposed in the study in terms of prediction accuracy on road with multiple bus routes.

Economic Analysis of Impacts of Sea Level Rise and Adaptation Strategies in Transportation

Although the causes of the sea level rise (SLR) are hotly debated, almost no disagreement exists that sea levels will continue to rise. The SLR is likely to have significant impacts on coastal transportation infrastructure. Adaptations in response to the SLR are in urgent need. Facing various adaptation strategies, decision makers need information on the impacts of different SLR scenarios as well as the economic trade-offs of various adaptation strategies. This research attempts to quantify the economic impacts of the SLR as well as the costs and benefits of adaptation strategies by using cost–benefit analysis at the local level. Hillsborough County, Florida, is used as a case study, and two projected scenarios for the SLR are applied to it. Light detection and ranging data, parcel land use data, and transportation network data for the county are employed to estimate the impacts of the two scenarios. Three adaptation strategies are suggested to the proposed SLR scenarios. Then cost–benefit analysis is conducted for each strategy under the two scenarios that consider the impacts of both direct inundation costs and indirect travel time costs. On the basis of the present values of the net benefits in the proposed strategies, managed retreat with critical infrastructure protection is the best adaptation strategy for the SLR in the long run and the length of shoreline protection is the most sensitive to the net benefits.

Hybrid Model for Prediction of Carbon Monoxide and Fine Particulate Matter Concentrations near a Road Intersection

Air quality time series near road intersections consist of complex linear and nonlinear patterns and are difficult to forecast. The backpropagation neural network (BPNN) has been applied for air quality forecasting in urban areas, but it has limited accuracy because of the inability to predict extreme events. This study proposed a novel hybrid model called GAWNN that combines a genetic algorithm and a wavelet neural network to improve forecast accuracy. The proposed model was examined through predicting the carbon monoxide (CO) and fine particulate matter (PM2.5) concentrations near a road intersection. Before the predictions, principal component analysis was adopted to generate principal components as input variables to reduce data complexity and collinearity. Then the GAWNN model and the BPNN model were implemented. The comparative results indicated that GAWNN provided more reliable and accurate predictions of CO and PM2.5 concentrations. The results also showed that GAWNN performed better than BPNN did in the capability of forecasting extreme concentrations. Furthermore, the spatial transferability of the GAWNN model was reasonably good despite a degenerated performance caused by the unavoidable difference between the training and test sites. These findings demonstrate the potential of the application of the proposed model to forecast the fine-scale trend of air pollution in the vicinity of a road intersection.

Identification and Prioritization of Critical Transportation Infrastructure: Case Study of Coastal Flooding

AbstractIn order to better inform transportation decision makers of the criticality of transportation infrastructure, this paper explores an accessibility-based criticality prioritization methodology to identify and prioritize critical transportation infrastructure. In particular, the methodology evaluates the network-wide impacts of infrastructure degradation based on the increase in travel cost taking origin importance, destination attractiveness, and traffic congestion into account. The methodology is applied to the road network of Hillsborough County, Florida, threatened by flood risk from storm surge, sea-level rise, and intense precipitation. Light detection and ranging digital elevation data, transportation infrastructure and network data, and zone-based population data of the county are processed for analysis. The approach yields results of not only the criticality of transportation infrastructure under flooding impact but also the most vulnerable zones as a result of infrastructure inundation. Th...

Analysis of Transportation Network Vulnerability Under Flooding Disasters

The transportation network plays an important role in peoples daily activities. At the same time, serious flooding disasters frequently damage the transportation infrastructure and network around the world. The vulnerability of the transportation network has attracted much attention. Understanding transportation network vulnerability can enhance prevention and response capabilities during disaster events and emergency incidents. However, current methods for evaluating transportation network vulnerability still have many disadvantages. This research provides an introduction to analysis of transportation network vulnerability, followed by a review of research addressing transportation network vulnerability. A new accessibility-based methodology addressing travel modes was developed to evaluate transportation network vulnerability under flooding impacts. A case study based on data from Hillsborough County, Florida, was conducted to verify the established model. ArcGIS was utilized to identify the inundated segments. Different flooding scenarios were applied in CUBE to update the shortest travel time changes under flooding. Networkwide accessibility and vulnerability values under each scenario were then calculated. Finally, accessibility values calculated with the proposed accessibility-based method and the Hansen accessibility index method were compared. Comparison of results shows that the results of the two methods are quite close, but the proposed method yields normalized values, which make the results clearer and provide more levels of accessibility loss. Research results of the study can support decision making for urban transportation under flooding disasters resulting from extreme weather events and sea level rise.

Tourist adaptation behavior in response to climate disasters in Bangladesh

ABSTRACT To assess the impacts of climate disasters on the behavior of tourists in Bangladesh, this study makes an initial attempt to investigate tourists’ adaptation behavior in response to climate disasters. A questionnaire survey was developed and administered to address both tourists’ previous adaptation behavior and their stated adaptation behavior in response to different future climate disasters. The choice modeling analysis of tourists’ previous behavior revealed that a cyclone is more likely to result in the cancellation of a trip, and a flood is more likely to result in a change in trip timing. As for the stated behavior analysis, it was confirmed that most variables related to disaster severity show significant influence on adaptation behavior. The results also indicate that construction of disaster-resilient transportation networks is essential to avoid trip cancellations. In addition, improving market-oriented tourism service quality in Bangladesh could play a significant role in reducing the probability of both trip cancellations and changes of destination. The findings of this study can provide the tourism industry in Bangladesh with critical insights for future disaster management and sustainable development of the tourism industry.

Prediction of vertical PM 2.5 concentrations alongside an elevated expressway by using the neural network hybrid model and generalized additive model

A study on vertical variation of PM2.5 concentrations was carried out in this paper. Field measurements were conducted at eight different floor heights outside a building alongside a typical elevated expressway in downtown Shanghai, China. Results show that PM2.5 concentration decreases significantly with the increase of height from the 3rd to 7th floor or the 8th to 15th floor, and increases suddenly from the 7th to 8th floor which is the same height as the elevated expressway. A non-parametric test indicates that the data of PM2.5 concentration is statistically different under the 7th floor and above the 8th floor at the 5% significance level. To investigate the relationships between PM2.5 concentration and influencing factors, the Pearson correlation analysis was performed and the results indicate that both traffic and meteorological factors have crucial impacts on the variation of PM2.5 concentration, but there is a rather large variation in correlation coefficients under the 7th floor and above the 8th floor. Furthermore, the back propagation neural network based on principal component analysis (PCA-BPNN), as well as generalized additive model (GAM), was applied to predict the vertical PM2.5 concentration and examined with the field measurement dataset. Experimental results indicated that both models can obtain accurate predictions, while PCA-BPNN model provides more reliable and accurate predictions as it can reduce the complexity and eliminate data co-linearity. These findings reveal the vertical distribution of PM2.5 concentration and the potential of the proposed model to be applicable to predict the vertical trends of air pollution in similar situations.

Job and residential location changes responding to floods and cyclones: an analysis based on a cross-nested logit model

With the increasing impacts of climate change, many people in Bangladesh are being forced to move their homes and/or change their jobs. Unfortunately, little is known about how people jointly decide on their jobs and residential location changes in association with the influence of climate change disasters. The main purpose of this paper is to examine how residents in coastal and inland areas may change their jobs and/or residential location under different scenarios of potential impacts of floods and cyclones by comparing socioeconomic and experiential factors. A stated preference survey was conducted in 14 coastal and inland areas of Bangladesh. As a result, 788 respondents provided 3152 valid samples (1948 from coastal areas and 1204 from inland areas). Analysis results based on a cross-nested logit model indicate that flood has no obvious impact on choices of inland people, and flood and cyclone have limited effects on people’s choices in coastal areas, except for cyclone intensity. Income is not significant in the decisions of the coastal people, but it does matter to the inland people. The inland people are more likely to depend on government help during disasters. However, the coastal people’s decisions are driven by different factors in a complicated way. The inland people prefer changing their jobs to changing their residential locations, but the coastal people are slightly more aggressive in deciding to change their residential location in response to flood. Structural differences of choice behaviors under flood and cyclone are also revealed. Finally, policy implications are discussed.

Comparison of SMS Calculation Methods Based on NGSIM Data for UAV Detection

The introduction of UAV into transportation offers a great number of challenges such as how to utilize the collected vehicle data of different levels to obtain traffic variables. Meanwhile, different detection approaches may acquire different types and precisions of vehicle data, and the methods that will be chosen for each detection approach also may vary. The main objective of this paper is to compare the difference of several methods of calculating space mean speed (SMS), so as to provide guidance for SMS calculation and application based on various detection data of UAV. Two basic methods and three expanded methods that are possible to be used for UAV detection to calculate SMS of a road are discussed based on a dataset from NGSIM. Without considering the errors that may be caused by instability of UAV flight and video processing, differences among the methods are analyzed in the MatLAB software. The results of the two basic methods are of large difference, and the expanded methods used to estimate the SMS in various time periods will also generate different results. So when the results obtained by these methods are used for data fusion and other transportation applications, they should be assigned different weights. Some other results are obtained too, which may provide references for the traffic parameter extraction based on UAV detection, and the data fusion between the space mean speed from UAV detection and that from other traffic detection methods.

The interrelationship between travel behavior and life choices in adapting to flood disasters

Abstract Disasters resulting from climate change are shown to be important determinants of people’s life choice decisions. In the literature, travel behavior choice and life choices are usually addressed separately under disasters such as flood and cyclone. However, travel behavior may be interdependent with other life choices, jointly shaping people’s adaptation decisions. To this end, the paper advances the literature by exploring the interrelationship between changes in travel behavior and job and residential location under flood disasters, while separating coastal and inland observations. For this purpose, a stated preference survey was conducted in 14 cities of Bangladesh in early 2013. An analysis approach based on structural equation modeling was developed to investigate the correlations between travel behavior change and job and residential location changes. Model estimation results suggest that flood impacts have significant influences on inland people’s life choices, while coastal people’s life choices are mainly affected by flood adaptation responses and attitudes. Significant correlations between travel behavior change and job and residential location changes are found for both observations. Moreover, both coastal and inland people tend not to change residential locations if changes in job location and travel behavior are made. Inland people may not change travel behavior if their job and/or residential locations are changed, but coastal people’s job and residential location changes are associated with changes in travel behavior. Travel behavior change is found to have more of an effect on residential location change than job location change in both regions. These findings conclude that the two-way relationship between travel behavior and life choices should be taken into account in future analyses, and thus adaptation policies to climate change disasters could be better linked with people’s behavioral responses.