Project scope

Status: Active

Mission: The UrbanSim Python library provides methods and reusable model components for building self-managed simulations of urban development, household and employment location, real estate markets, and related regional change.

Architecture: UrbanSim is a portable, self-managed Python library designed primarily for conventional CPU-based execution. It provides reusable model components and interfaces that can also be implemented by other execution engines.

The project maintains and develops:

• statistical model components used in urban simulation;

• location-choice, relocation, transition, and development models;

• real-estate feasibility and related urban-development methods;

• estimation and simulation utilities;

• model APIs and configuration patterns; and

• reusable components for assembling regional UrbanSim implementations.

UrbanSim is designed to work with other UDST libraries and with external data, estimation, accessibility, and workflow systems through documented Python interfaces and model specifications.

Development of urban-simulation methods and reusable model components is welcome within this mission and architecture. Material changes to the project’s mission or execution architecture are considered through UDST’s organization-level governance process.

See the UDST Project Directory and Open-source projects and commercial offerings for organization-wide project status and policy.

How it works

Operational UrbanSim models begin with detailed data about a particular region, and then estimate and validate a system of interconnected model components. Full models draw on a number of libraries: not just urbansim, but also Orca for task orchestration, Synthpop for population synthesis, Pandana for network analysis, and so on. Collectively, these make up the Urban Data Science Toolkit (UDST).

UrbanSim models are used by public agencies, consultancies, and researchers in dozens of cities around the U.S. and world. The core platform is open source, but many operational models make use of additional cloud-hosted model building and visualization tools provided by UrbanSim Inc.

Learn More

• An Introduction to UrbanSim

• UrbanSim for San Francisco: An example implementation

• UrbanSim Inc.

Installation

UrbanSim requires Python 3.10 or later.

• pip install urbansim

• conda install urbansim --channel conda-forge

The network accessibility utilities also require Pandana, which is optional: pip install "urbansim[network]".

Technical documentation

• Getting started

• Full documentation

• Other UDST libraries

• Documentation for UrbanCanvas, the UrbanSim cloud platform