Reference · AI & Analytics Atlas
AI & Analytics Atlas
Discover how artificial intelligence, machine learning, and advanced analytics help cities monitor operations, predict conditions, optimize services, and support decisions.
Browse AI & Analytics Atlas
17 of 17 published entries · Checking additional published records…
AI agents for bounded city workflows
Software that can plan and call tools, with permissions limited to its task.
Read entry →Anomaly detection for urban infrastructure
Finding a meaningful deviation before it disappears into routine variation.
Read entry →Classification algorithms for urban operations
Assigning observations to defined categories while keeping uncertainty visible.
Read entry →Clustering for urban pattern discovery
Grouping similar observations without preassigned categories.
Read entry →Computer vision for urban systems
Turning images into measurements that still need context, governance, and human review.
Read entry →Digital twins and urban analytics
Connecting a digital representation to evidence about a changing physical place.
Read entry →Edge AI for urban infrastructure
Running a model near the sensor while managing updates, uncertainty, and device limits.
Read entry →Geospatial analytics for city decisions
Understanding how urban conditions vary by location, network, and neighborhood.
Read entry →Large language models in city services
A fluent text interface that can still be incomplete, outdated, or wrong.
Read entry →Natural language processing for public services
Working with written or spoken language while preserving human accountability.
Read entry →Optimization for urban networks
Choosing among feasible operating plans under explicit goals and constraints.
Read entry →Regression algorithms for city measurement
Estimating a numeric value and understanding the error around it.
Read entry →Reinforcement learning for urban operations
Learning action policies through feedback in a carefully bounded environment.
Read entry →Retrieval-augmented generation for city information
Grounding generated answers in documents that can be inspected and updated.
Read entry →Simulation and scenario modeling for cities
Testing assumptions in a model before changing real streets, buildings, or services.
Read entry →Supervised learning for city data
Learning a mapping from labeled examples, then checking where it works and where it fails.
Read entry →Time-series forecasting for cities
Estimating what comes next from measurements ordered in time.
Read entry →