Merkebe Getachew Demissie

The rapid growth of dockless electric scooter (e-scooter) sharing services has transformed short-distance urban mobility, offering convenience and sustainability benefits while amplifying challenges related to demand imbalance, fleet rebalancing, and spatial inequity. Accurate spatiotemporal demand prediction is therefore essential for optimizing resource allocation and supporting data-driven policy interventions. This study proposes a hybrid deep learning framework that integrates a Graph Convolutional Network (GCN) with a Gated Recurrent Unit (GRU) and community detection to enhance short-term prediction of e-scooter pick-up and drop-off demands. The Louvain algorithm is employed to partition urban areas into mobility-based communities, enabling the model to capture functional connectivity rather than relying solely on geographic proximity. Using real-world e-scooter trip data from Calgary, Canada, the model’s performance is evaluated against established baselines, including a Masked Fully Convolutional Network (MFCN) and conventional GRU architectures. Results show that the proposed approach achieves up to 11.8% improvement in mean absolute error (MAE) compared with the MFCN baseline and more robust generalization across temporal horizons. The findings demonstrate that integrating community structures into graph-based learning effectively captures complex urban dynamics, providing practical insights for sustainable micromobility operation and service deployment.

Temporary migration trips are circulatory journeys that can be associated with tourism as these trips aren’t made on a regular basis. They’re often left unmeasured due to limited data sources, and thereby missing from regional and national travel demand models. This article presents a methodology for inferring large-scale temporary migration trips from mobile phone network data or Call Detail Record (CDR), and analyzing their spatial determinants based on urban assets derived from Google Places data. As a case study, CDR of mobile phone users in Portugal was used in our study from which insightful statistical patterns of both intra and inter-district flows were observed. Analysis of spatial determinants shows that places for leisure and population density are among the top influential factors that attract inflows into the district, while places for public service such as city hall, local government office, courthouse, and cemetery are negative urban assets for attracting district’s inflows. The presented methodology and insights gained from our analysis can be useful for transport and urban planners to establish better informed travel demand modeling and urban planning strategies.

Dockless electric scooters (e-scooter) have emerged as a green alternative to automobiles and a solution to the first- and last-mile problems. Demand anticipation, or being able to accurately predict spatiotemporal demand of e-scooter usage, is one supply–demand balancing strategy. In this paper, we present a dockless e-scooter demand prediction model based on a fully convolutional network (FCN) coupled with a masking process and a weighted loss function, namely, masked FCN (or MFCN). The MFCN model handles the sparse e-scooter usage data with its masking process and weighted loss function. The model is trained with highly correlated features through our feature selection process. Next-hour and next 24-h prediction schemes have been tested for both pick-up and drop-off demands. Overall, the proposed MFCN outperforms other baseline models including a naïve forecasting, linear regression, and convolutional long short-term memory networks with mean absolute errors of 0.0434 and 0.0464 for the next-hour pick-up and drop-off demand prediction, respectively, and the errors of 0.0491 and 0.0501 for the next 24-h pick-up and drop-off demand prediction, respectively. The developed MFCN expands the collection of deep learning techniques that can be applied in the transportation domain, especially spatiotemporal demand prediction.

The movement of trucks represents a significant portion of travel. Surveys have traditionally been used to measure truck movement, but this costly and limited data collection method typically involves in-person interviews and requiring high workload. This study explores different ways in which passive truck GPS data can be used to complement traditional data collection methods, for obtaining detailed information about the travel behaviors of freight trucks. First, we develop a heuristic-based model to identify truck stops. A new methodology is proposed to classify truck stops into a primary or secondary sto, which make identifying trip purposes possible. Primary stops are defined as the locations where the loading or unloading of the goods takes place. Secondary stops are those associated with all other purposes, including refueling, and driver breaks. Finally, we develop a destination choice model for modeling truck movements. This model applies a discrete choice modeling technique to distribute truck trips within the Calgary region, Canada. We test the utility function in the destination choice model to include of business establishment data, travel impedances, and other dummy variables that are likely to influence truck demand. The results show that a combination of trucks’ dwelling times and their entropy can be used to classify truck stops by purpose. This study also shows the potential of using passive GPS data to gain additional insights into truck movements characterization and truck trip distribution modeling.