Urban AI 2024

2nd ACM SIGSPATIAL International Workshop on
Advances in Urban-Al
(Urban-Al 2024)
Tuesday, October 29, 2024
Atlanta, GA, USA

The 2nd ACM SIGSPATIAL International Workshop on Advances in Urban AI brings together researchers and practitioners to discuss advancements and future directions in urban AI. Urban AI is an emerging field that combines AI, spatial computing, and urban science to address complex challenges faced by cities. The availability of extensive urban data and the growth of digitized city infrastructures have opened opportunities for data-driven machine learning approaches in urban science. Urban AI encompasses innovative AI techniques applied to urban problems, AI-ready urban data infrastructure, and various urban applications benefiting from AI. Its applications range from urban planning and design to traffic prediction, energy management, public safety, urban agriculture, and land use.

In the era of digital transformation, cities are becoming smarter, more sustainable, and efficient. Urban AI leverages data collected from sensors, satellites, and IoT devices to enable evidence-based decision making. Real-time analysis of climate patterns, infrastructure performance, energy consumption, and social dynamics helps identify vulnerabilities, optimize resource allocation, and inform climate resilience strategies. Urban AI R&D takes this concept to new heights by utilizing advanced AI algorithms, machine learning, and extensive data analytics to establish intelligent urban ecosystems. These ecosystems integrate various urban domains, fostering cohesive operations, data-informed decision making, and improved citizen experiences. Considering the complexity and heterogeneity of urban information, spatiotemporal aspects such as location, distance, shape, and spatial patterns must be carefully considered and incorporated into urban AI R&D to address geospatial challenges in urban environments.

Call for Papers

The 2024 Urban-AI workshop invites papers in the following topics (but not limited to):