In the case of missing data, traffic forecasting becomes challenging. Many existing studies on traffic flow forecasting with missing data often overlook the relationship between data imputation and external factors. To address this gap, this study proposes two hybrid models that incorporate multiple factors for predicting traffic flow in scenarios involving data loss. Temperature, rainfall intensity and whether it is a weekday will be introduced as multiple factors for data imputation and forecasting. Predictive mean matching (PMM) and K-nearest neighbor (KNN) can find the data that are most similar to the missing values as the interpolation value. In the forecasting module, bidirectional long short-term memory (BiLSTM) network can extract bidirectional time series features, which can improve forecasting accuracy. Therefore, PMM and KNN were combined with BiLSTM as P-BiLSTM and K-BiLSTM to forecast traffic flow, respectively. Experiments were conducted using a traffic flow dataset from the expressway S6 in Poland, considering various missing scenarios and missing rates. The experimental results showed that the proposed models outperform other traditional models in terms of prediction accuracy. Furthermore, the consideration of whether it is a working day further improves the predictive performance of the models.
Online car-hailing is gradually shifting towards a predominant use of electric vehicles, a change that is advantageous for developing a sustainable society. Understanding the patterns of changes in online car-hailing travel can assist transportation authorities in optimizing vehicle dispatching, reducing idle rates, and minimizing resource wastage. The built environment influences the demand for online car-hailing travel. Previous studies have commonly employed the geographically weighted regression (GWR) model and the geographically and temporally weighted regression (GTWR) model to examine the relationship between the demand for online car-hailing trips and the built environment. However, these studies have ignored that the impact range of the built environment also varies with time and space. To fully consider the variations in the impact range of the built environment, this study established multi-scale geographically and temporally weighted regression (MGTWR) to examine the spatiotemporal impacts of urban built environments on the demand for online car-hailing travel. An empirical study was conducted to assess the effectiveness of the MGTWR model using point of interest (POI) data and online car-hailing order data from Haikou. The evaluation indicators showed that the MGTWR model has higher fitting accuracy than the GTWR model. Moreover, the impact of each type of POI on the demand for online car-hailing travel was analyzed by examining the temporal and spatial distribution of the regression coefficients. Additionally, we observed that transport facility POIs and healthcare service POIs exerted the most pronounced influence on the demand for online car-hailing. In contrast, the impact of shopping service POIs and catering service POIs was relatively weaker.
High precision in forecasting travel demand for online car-hailing is crucial for traffic management to schedule vehicles, hence reducing energy consumption and achieving sustainable development. Netflix demand forecasting relies on the capture of spatiotemporal correlations. To extract the spatiotemporal information more fully, this study designs and develops a novel spatiotemporal prediction model with multidimensional inputs (MSACL) by embedding a self-attention memory (SAM) module into a convolutional long short-term memory neural network (ConvLSTM). The SAM module can extract features with long-range spatiotemporal dependencies. The experimental data are derived from the Chengdu City online car-hailing trajectory data set and the external factors data set. Comparative experiments demonstrate that the proposed model has higher accuracy. The proposed model outperforms the Sa-ConvLSTM model and has the highest prediction accuracy, shows a reduction in the mean absolute error (MAE) by 1.72, a reduction in the mean squared error (MSE) by 0.43, and an increase in the R-squared (R2) by 4%. In addition, ablation experiments illustrate the effectiveness of each component, where the external factor inputs have the least impact on the model accuracy, but the removal of the SAM module results in the most significant decrease in model accuracy.