Bio:

Dr. Songnian Li received his Ph.D. degree in geodesy and geomatics engineering from the University of New Brunswick in 2002. He is a Professor in the Department of Civil Engineering, Toronto Metropolitan University, Canada. His current research interests include geospatial big data, spatiotemporal analysis, human mobility, geo-collaboration, and smart cities (digital twin). He has served as the Executive-Editor-in-Chief of the Big Earth Data journal and the Editor-in-Chief of the Canadian Journal of Remote Sensing. He is an ISPRS Fellow and currently serves as the Chair of UN-GGIM Academic Network. He is also an Executive Director of the Canadian Remote Sensing Society.

Talk Title:

Geosocial Sensing: Human Activity Patterns Empowered Traffic Event Detection

Abstract:

The vast amount of crowdsourced social media data has opened new frontiers in understanding urban mobility and improving intelligent transportation systems. This talk examines how human activity patterns derived from geosocial media data can empower traffic event detection with greater accuracy, timeliness, and contextual awareness. Unlike traditional sensor-based approaches, geosocial data, such as geotagged tweets, posts, and check-ins, capture the real-time pulse of human movement and collective behavior. By analyzing spatial, temporal, and semantic patterns in this data, traffic events may be detected in real time or near-real time. The presentation will explore challenges in using geosocial media data, how spatiotemporal modeling of human activity enables more accurate and timely detection of incidents, congestion, and disruptions, and key methodologies that enable robust traffic incident identification. This presentation underscores the potential of geosocial media as a powerful complementary data source for next-generation, human-centered intelligent transportation systems by addressing some future directions.