CfP GeoAI and Deep Learning Symposium: GeoAI and Urban Mobility Analytics

The integration of Geospatial Artificial Intelligence (GeoAI) with urban mobility analytics is paving the way for groundbreaking insights into the complex dynamics of cities and their transportation networks. This rapidly developing field harnesses the power of AI, including machine learning, deep learning, and big data mining, combined with geospatial science to address urban mobility challenges and optimize transportation systems for more efficient and sustainable urban living.

Urban mobility, a cornerstone of modern urbanization involves how people, goods, and services move around a city. Leveraging GeoAI allows researchers and practitioners to analyze vast amounts of spatiotemporal data, uncover hidden patterns, forecast demand, and propose data-driven strategies to understand daily mobility patterns, improve traffic flow, enhance public transit systems, and promote active transportation modes. Deep learning, with its ability to model non-linear, intricate relationships, is instrumental in understanding the interactions between urban infrastructure, human behavior, and external factors such as socio-economic conditions and environmental changes.

For the American Association of Geographers Annual Meeting next year (AAG 2025), we are organizing a paper presentation session as part of the GeoAI and Deep Learning Symposium.  We invite scholars, data scientists, urban planners, and practitioners to share innovative research, methodologies, and real-world applications that leverage GeoAI to address urban mobility challenges. We especially welcome studies that focus on, but are not limited to AI approaches to:

  • Human Mobility Behavior Analysis Using Geodata
  • Spatial-Temporal Analysis of Urban Mobility
  • Modeling Active or Micro-Mobility Patterns in Cities
  • Analyze the role of micro-mobility and emerging mobility services through AI-driven insights.
  • Integrate deep learning models to optimize public and active transport networks.
  • Investigate urban mobility patterns in response to policy changes or urban development.
  • Utilize multi-modal data sources to model and predict urban movement trends.
  • Explore resilience in urban mobility, especially under disruptions or crises.
  • Understanding the Impact of Autonomous Vehicles (AVs) and Electric Vehicles (EVs)on Urban Mobility and Travel Patterns through Geo-Spatial Data
  • Spatial Disparities in Access to EV Charging Infrastructure and Its Social Impact
  • Transportation Demand Prediction and Optimization
  • GeoAI Approaches for Understanding Urban Traffic Congestion
  • Methods for Enhancing Public Transportation Efficiency and Accessibility
  • Planning Infrastructure for Autonomous and Electric Vehicles
  • Measuring Urban Vibrancy and Mobility Vitality
  • Real-Time Mobility Management for Smart Cities
  • Equity Analysis in Urban Mobility
  • Quantifying uncertainties in urban mobility data for improved transport modeling
  • Assessing the impact of shared mobility on urban traffic patterns

The aim of this session is to foster cross-disciplinary collaboration and highlight state-of-the-art research that can inform policies, support urban sustainability, and contribute to the smarter design of cities. We welcome submissions that span from theoretical advances to practical applications in urban mobility and invite contributors to showcase how their work is reshaping the landscape of urban analytics through GeoAI.

Submission Guidelines: If you are interested in joining this session, please email your name, organization, talk title, AAG PIN, abstract, and contact information to the following organizers before the deadline (December 5, 2024).

Organizing Team:
  • Dan Qiang, McGill University (dan.qiang@mail.mcgill.ca)
  • Grant McKenzie, Associate Professor, McGill University (grant.mckenzie@mcgill.ca)
  • Xiao Huang, Assistant Professor, Emory University (xiao.huang2@emory.edu)
  • Yihong Yuan, Associate Professor, Texas State University (yuan@txstate.edu)
LinkedIn