Artificial intelligence-enabled digital twin for U.S. cities

The Science

Experts from laboratories, universities, industry, and the city of Chicago met to discuss the use of an Artificial Intelligence–Enabled Digital Twin (AIDT) for areas such as energy consumption, water management, and other urban systems. A digital twin is a virtual copy of a real urban system. AIDT assists in studying system behavior and interactions of multiple components in the urban system. At this meeting, researchers shared insights found using simulations, sensor networks, and AI tools to model weather, energy use, and infrastructure responses. Chicago was the testbed. Data from an AIDT can help stakeholders gain timely insights for safer and more efficient operations.

The Impact

AIDT opens new ways for urban planners and engineers to test ideas without costly experiments. The digital twin paves the way for responsive designs and better resource management. It can help optimize building codes, energy use, and emergency responses. The approach may guide investments that improve urban resilience while supporting efficient operations. With clear, data‑driven insights, cities can plan for future challenges more confidently.

Summary

At a July 2025 workshop held at the U.S. Department of Energy’s Argonne National Laboratory, over 50 researchers and stakeholders came together to discuss an AIDT for urban systems. The workshop highlighted how Chicago Urban Integrated Field Laboratory’s rich datasets, including high‑resolution urban models, alongside multi-scale observations from street to city level, can form a testbed for digital twin development. Attendees reviewed advanced simulation techniques and AI architectures that integrate detailed 3D urban geometries, turbulence models, and real-time sensor data. These approaches support rapid iteration and uncertainty-aware forecasting for urban weather, energy use, urban planning, and emergency management. The work builds on Argonne’s existing foundation model initiatives and aims to create a scalable prototype to help cities adapt and plan efficiently. Future steps include integrating more urban data and closer collaboration with engineers to build a trusted, transparent tool for urban planning.