Accurate demand prediction plays a significant role in online car-hailing platforms. With ensemble learning, several models can be combined into a single demand predictive model, achieving low prediction error. Nevertheless, the existing ensemble methods are not intended for spatio-temporal data and thus cannot deal with it. In this article, a spatio-temporal data ensemble model is proposed to predict car-hailing demands. Treating the prediction results as various channels of an image, the proposed ensemble module first compresses and then restores the results using the fully convolutional network. Additionally, a skip connection is used to preserve both the fine-grained information in the shallow layers and the deep coarse information. Based on the principle of model as a service, any model can be plugged into our framework as base models to improve the prediction accuracy. Experimental results demonstrate the effectiveness of the presented model.

With the rapid increasing of car usage, congestion is becoming more and more severe in metropolitans. To tackle this problem, the classification and prediction of traffic states are vital for the authority to quickly react. This study proposes a machine learning method to identify and predict traffic states at small region levels. In this paper, we compare two different spatial division methods, namely rectangular grids and hexagonal grids and measure the traffic characteristics through aggregating floating car trajectory data. Then a dimensionality reduction technique is applied to the traffic parameter, followed by a clustering model for traffic state recognition and labeling. From the analysis in this study, speed is found to be an important feature for classifying the traffic state. Therefore, two Convolutional Neural Network (CNN) models using different architecture were used for both speed and traffic state prediction, which could consider the spatial and temporal features simultaneously. Random forest regression, Gradient boosting decision tree and Long-short term memory neural network model are used as baseline models. The case study performed in Chengdu demonstrates that the proposed model outperforms the baseline models.

The link performance and capacity are important quantitative features in road link performance assessment, and they play vital roles in many important transportation tasks, e.g., traffic assignment and dynamic routing. However, it remains a challenging task to quantify them, particularly in a dynamic traffic scenario requiring an accurate, fast, and dynamic output. This study proposes a tailored deep learning framework for the addressed problem, which combines important transport domain knowledge reflected by the Bureau of Public Road (BPR) link performance function. In specifics, the calibration of link performance function and the estimation of link travel time are combined in the proposed framework and realized by two neural network modules. Numerical experiments demonstrate the capability of the proposed framework to capture complex relationships between dynamic link capacity and various factors and show its value in estimating link travel time.

Intermodal transfer patterns could provide a better understanding of urban mobility in an integrated transit system. However, the existing literature is still limited related to in-depth data-driven investigations of transfer patterns, particularly between metro and bus. In this study, we propose a generic framework to unravel latent transfer patterns at both aggregated and disaggregated levels. K-means clustering method is first used to classify metro stations based on surrounding built environment. We then introduce the cube technique which allows hierarchical aggregations for each dimension and cross-tabulations of massive ridership data. Last, we redesign the generative mechanism of the structural topic model that is capable of capturing the variability and interdependence in transfer patterns with passenger-level attributes. An empirical study is conducted with large-scale metro and bus smart card data, as well as built environment data in Nanjing, China. The results indicate intermodal transfers exhibit significant heterogeneous patterns in different transfer types over space and time. Although transfers per station in central business district (CBD) areas rank the highest, urban sprawl helps increase the utilization rate of transfer services in inner suburbs with most types of transfer behaviors. Strong correlations are identified among commuting transfer patterns, while correlations remain weak for pattern pairs between commuting and non-commuting activities, reflecting high consistency among commuting activities. Adults play a dominant role in commuting patterns in CBD areas and inner suburbs. Yet, students and the elderly are found to influence the pattern prevalence more effectively in outer suburbs and periphery areas.

Crash injuries not only result in huge property damages, physical distress, and loss of lives, but arouse a reduction in roadway capacity and delay the recovery progress of traffic to normality. To assess the resilience of post-crash tunnel traffic, two novel concepts, i.e., surrogate resilience measure (SRM) and injury-based resilience (IR), were proposed in this study. As a special kind of semi-closed infrastructure, urban tunnels are more vulnerable to traffic crashes and injuries than regular roadways. To assess the IR of the post-crash roadway tunnel traffic system, an over-one-year accident dataset comprising 8621 crashes in urban roadway tunnels in Shanghai, China was utilized. A total of 34 variables from 11 factors were selected to establish the IR assessment indicator system. Methodologically, to tackle the skewness issue in the dataset, a binary skewed logit (Scobit) model was found to be superior to a conventional logistic model and subsequently adopted for further analysis. The estimated results showed that 15 variables were identified to be significant in assessing the IR of the roadway tunnels in Shanghai. Finally, the formula for calculating the IR levels of post-crash traffic systems in tunnels was given and would be a helpful tool to mitigate potential trends in crash-related resilience deterioration. The findings of this study have implications for bridging the gap between conventional traffic safety research and system resilience modeling.