Deep Learning in Current Transportation Systems

Dear Colleagues,

Deep learning has been widely used in transportation systems such as road transportation, railway transportation, metro transportation, air transportation, with broad applications including vehicle routing, timetable scheduling, airport ground handling, as well as vehicle and pedestrian detection, spatial-temporal traffic prediction, operational decision-making, delay prediction and so on. The commonly used deep learning models in transportation systems include Transformers, Graph Neural Networks, GFlowNets, Diffusion models, Autoencoders, Convolutional Neural Networks, Recurrent Neural Networks, to name a few. However, deep learning still encounters challenges in effectively addressing the uncertainty, ever-changing dynamics, traffic disruption and incident in large-scale transportation networks. Hence the reliability of deep learning techniques remains insufficient for facilitating decision making and operational tasks in real-world transportation systems. This special issue aims to push the frontier of deep (reinforcement) learning towards solving complex decision making and prediction tasks in transportation, and thereby facilitate the operational efficiency and resilience of transportation systems. The special issue encourages applications or creations of various deep learning techniques in transportation systems.

In this Special Issue, original research articles and reviews are welcome. Topics of interest for this special issue include, but are not limited to:

• Vehicle routing problems (TSP, CVRP and their variants) with deep learning
• Joint optimization of location, inventory and routing problems
• Network design problems with deep learning
• Data-driven train timetable optimization and maintenance scheduling
• Neural network based train unit shunting problems
• Neural airport ground handling
• Learning assisted crew and roster scheduling
• Data-driven metro scheduling or rescheduling
• Deep reinforcement learning for predictive aircraft maintenance
• Neural multi-objective optimization in vehicle routing problems
• Neural stochastic/robust optimization in transportation
• Traffic flow/time/sign/demand prediction
• Traffic accident risk prediction
• Vehicle and pedestrian detection/identification
• Driver behavior detection and classification
• Traffic signal control with deep learning
• Data-driven path planning for unmanned aerial vehicles
• Trajectory prediction and learning based urban navigation
• Delay prediction on transportation networks
• Spatial-temporal prediction on transportation networks

We look forward to receiving your contributions.

Dr. Yaoxin Wu
Dr. Zhenkun Wang
Prof. Dr. Mingyao Qi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• deep learning
• neural network
• optimization, traffic prediction and detection, vehicle routing
• traffic control
• timetable scheduling
• path planning
• airport operations management
• train unit shunting