Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graphs

In recent years, ride-hailing services have been increasingly prevalent, as they provide huge convenience for passengers. As a fundamental problem, the timely prediction of passenger demands in different regions is vital for effective traffic flow control and route planning. As both spatial and temporal patterns are indispensable passenger demand prediction, relevant research has evolved from pure time series to graph-structured data for modeling historical passenger demand data, where a snapshot graph is constructed for each time slot by connecting region nodes via different relational edges (origin-destination relationship, geographical distance, etc.). Consequently, the spatiotemporal passenger demand records naturally carry dynamic patterns in the constructed graphs, where the edges also encode important information about the directions and volume (i.e., weights) of passenger demands between two connected regions. aspects in the graph-structure data. representation for DDW is the key to solve the prediction problem. However, existing graph-based solutions fail to simultaneously consider those three crucial aspects of dynamic, directed, and weighted graphs, leading to limited expressiveness when learning graph representations for passenger demand prediction. Therefore, we propose a novel spatiotemporal graph attention network, namely Gallat ( G raph prediction with all at tention) as a solution. In Gallat, by comprehensively incorporating those three intrinsic properties of dynamic directed and weighted graphs, we build three attention layers to fully capture the spatiotemporal dependencies among different regions across all historical time slots. Moreover, the model employs a subtask to conduct pretraining so that it can obtain accurate results more quickly. We evaluate the proposed model on real-world datasets, and our experimental results demonstrate that Gallat outperforms the state-of-the-art approaches.

Demand Estimation of Proposed Bus Rapid Route in Al Kut City

Public transit in the city of Al-Kut faces great challenges due to the weakness of the local government abilities in providing adequate conditions for public transport such as wide vehicles, comfortable seats, and other environmentally friendly means of transport that are almost non-use in the city of Kut, where the dependence is heavily on Mini Bus (Kia) and a medium-sized bus, most of which are old, do not operate in an integrated way, compete with each other for the passengers, reduce the flexibility of movement. This study attempts to estimate the demand for the proposed bus rapid route in the city of al Kut as a modern public transport that can contribute to reducing congestion in the city. In this study, the demand for the current public transport network lines in the city was studied, which are 12 lines using boarding / alighting values to determine passenger loads and assess flow on each route in the transportation network using the origin-destination (OD) data from on/off data, then repeat the application on the BRT route, this was done using assignment model in TransCAD software, where the results showed an estimated value for passenger demand on BRT route about 7,616 passengers/hour, which is equivalent to 40.12 % of the transport lines service.

Description of multimodal transport networks by means of graph models

The main objective of organising multimodal transport is to meet the public’s demand for transport services as much as possible while making the most efficient use of rolling stock. In order to determine the efficiency of a transport system the paper proposes that it should be viewed as a collection of different local transport systems. The issue of organising multimodal transport is related to many aspects of passenger services and rail transport operations (forecasting passenger flows, developing combined train schedules, features of the TH (transfer hub) and station complexes, etc.). The article details the way multimodal passenger chains are represented in the form of graphical models. The goals of using the constructed graphs are defined: solving problems of visualisation and analysis of multimodal transport chains as well as solving the complex problem of optimising the scheduling and planning of vehicle stops at passenger transfer points. It has been shown that the main requirements for organising this type of passenger transport are to minimise the total travel time of vehicles in order to reduce management costs for operators and to maximise the number of passengers carried in order to better meet passenger demand.

Estimating the Reduction in Future Fleet-Level CO2 Emissions From Sustainable Aviation Fuel

With rising concerns over commercial aviation’s contribution to global carbon emissions, the aviation industry faces tremendous pressure to adopt advanced solutions for reducing its share of CO2 emissions. One near-term potential solution to mitigate this global emissions situation is to operate existing aircraft with sustainable aviation fuel (SAF); this solution requires almost no modification to current aircraft, making it the “quickest” approach to reduce aviation carbon emissions, albeit the actual impact will be determined by the degree to which airlines adopt and use SAF, the ticket price impact of SAF, and the future growth of travel demand. This article presents results that estimate the expected fleet-wide emissions of future airline operations using SAF considering various projected traveler demand and biofuel penetration/utilization levels. The work demonstrates an approach to make these predictions by modeling the behavior of a profit-seeking airline using the Fleet-Level Environmental Evaluation Tool (FLEET). Considering five future SAF scenarios and two future passenger demand projection scenarios, FLEET estimates future fleet-level CO2 emissions, showcasing the possible upper and lower bounds on future aviation emissions when SAF is introduced for use in airline fleets. Results show that the future fleet-level CO2 emissions for all scenarios with SAF are lower than the baseline scenario with no SAF, for all demand projection scenarios. The passenger demand served and the trips flown for a given SAF scenario depends on the SAF price and the biofuel penetration levels. This shows that even if airlines serve a higher passenger demand for some future scenarios, the carbon emissions could still be lower than the current baseline scenario where airlines only use conventional jet fuel.

Air Transport Demand Forecast to Making the Regional Aviation Sustainable in Northeast of Brazil

Both researchers and Government Agencies see aviation as an important driver for regional development and national integration. Thus, this sector has been a matter of concern for the government who has ways to stimulate the aero activity. The Regional Aviation Development Program (PDAR) has been currently under development implemented in Brazil. This program foresees public investments in airport infrastructure and operational subsidies for airlines to enhance the sector operation and increase the number of locations served by regional aviation. This paper presents a model for estimating passenger demand potential through multiple linear regression to cover the great majority of the federative units (states) of Pernambuco, Paraíba, Rio Grande do Norte, Ceará, and Piauí in the northeast of Brazil. Subsequently, localities are suggested to optimize the resources of the PDAR, and we concluded that it is likely that there are regions with higher demand potential than some regions, which are already served by the airlines. Hence, we assumed that by strategically directing investments to specific localities, companies operate without subsidies, which in turn can be directed to airlines used to integrate the country. This making regional aviation more sustainable leading development to isolated localities, and thus efficiently contributing to reducing the Brazilian social inequality.

A Continuous Model for Designing Corridor Systems with Modular Autonomous Vehicles Enabling Station-wise Docking

The “asymmetry” between spatiotemporally varying passenger demand and fixed-capacity transportation supply has been a long-standing problem in urban mass transportation (UMT) systems around the world. The emerging modular autonomous vehicle (MAV) technology offers us an opportunity to close the substantial gap between passenger demand and vehicle capacity through station-wise docking and undocking operations. However, there still lacks an appropriate approach that can solve the operational design problem for UMT corridor systems with MAVs efficiently. To bridge this methodological gap, this paper proposes a continuum approximation (CA) model that can offer near-optimal solutions to the operational design for MAV-based transit corridors very efficiently. We investigate the theoretical properties of the optimal solutions to the investigated problem in a certain (yet not uncommon) case. These theoretical properties allow us to estimate the seat demand of each time neighborhood with the arrival demand curves, which recover the “local impact” property of the investigated problem. With the property, a CA model is properly formulated to decompose the original problem into a finite number of subproblems that can be analytically solved. A discretization heuristic is then proposed to convert the analytical solution from the CA model to feasible solutions to the original problem. With two sets of numerical experiments, we show that the proposed CA model can achieve near-optimal solutions (with gaps less than 4% for most cases) to the investigated problem in almost no time (less than 10 ms) for large-scale instances with a wide range of parameter settings (a commercial solver may even not obtain a feasible solution in several hours). The theoretical properties are verified, and managerial insights regarding how input parameters affect system performance are provided through these numerical results. Additionally, results also reveal that, although the CA model does not incorporate vehicle repositioning decisions, the timetabling decisions obtained by solving the CA model can be easily applied to obtain near-optimal repositioning decisions (with gaps less than 5% in most instances) very efficiently (within 10 ms). Thus, the proposed CA model provides a foundation for developing solution approaches for other problems (e.g., MAV repositioning) with more complex system operation constraints whose exact optimal solution can hardly be found with discrete modeling methods.

Analysis of Bus Passenger Demand and Supply: Case Study on Western Province, Sri Lanka

Buses carried about 47% of passengers crossing the Colombo Municipal Council (CMC) boundary in 2013. The Sri Lanka Transport Board (SLTB) and private bus companies operates roughly 680 intra-provincial bus routes and 400 inter-provincial bus routes in the Western Province according to the bus route information from the National Transport Commission (NTC, 2012) . The number of buses on the seven (7) major radial corridors carries more bus passengers than other roads in the Western Province. Kandy, Galle and Malabe Road corridors are the highest followed by High Level, Negombo, Horana and Low Level Road corridors. This research paper is an attempt to analyse the bus passenger demand and supply on seven major corridors connecting Western Province boundaries. The impact of the passenger demands and volumes from the seven major corridors and the traffic speed are the main outcome of this analysis. The present bus traffic information and the impact of the traffic congestion due to the high traffic flow on major corridors are discussed in the analysis. The research will also focus on alternative solutions and the importance of integrating other public transport modes to cater the demand from the major seven corridors for the better utilisation of public transport inside the Western Province boundaries.

Assessing Commuting Energy and Emissions Savings through Remote Working and Carpooling: Lessons from an Italian Region

Effective solutions are needed to decrease the greenhouse gases emissions of the transport sector, not only in terms of supply-side measures, but also including demand-side solutions. This paper focuses on the passenger demand related to daily commuting, either for work or study purposes. A bottom-up analysis is presented, which draws from detailed data for Lombardy, the most populous region in Northern Italy, to build an estimate of the annual energy consumption and emissions related to commuting. The potential of different measures to decrease emissions is evaluated, including the renovation of the vehicle stock, higher levels of remote working, and the deployment of carpooling schemes. The results show that the largest part of the current emissions from commuting is caused by car use, both due to its higher modal share and to the higher specific emissions, which are in turn also contributed by the low occupancy rates. The renewal of the current vehicle stock can lead to significant emission savings, thanks to both improved efficiency and higher shares of electrification. Remote working could also play a significant part, especially when it is applied to workers that face the longest commuting distances. Conversely, carpooling seems to be providing lower benefits, not so much because of lower effectiveness but more so because of constraints and barriers to its implementation.