A New Tool for Agent-Based Modeling

Comparing it to a far-more-accurate version of Sim City, Oscar Perry Abello covers Doppelgänger, an agent-based modeling tool from Google's Sidewalk Labs. Doppelgänger provides "real-world planners a simulation based not on some 1990-era coder's best approximation of people, but instead one based on the terabytes upon terabytes of real-world data available in today's digital world."

According to Sidewalk Labs modeling lead David Ory, "Doppelgänger enables planners to create a set of virtual households that accurately reflects real neighborhoods, cities, regions, or states, along any dimension relevant to the problem at hand. [It] can create households that have accurate numbers of children, seniors, teachers, persons with disabilities, electric-vehicle owners, swing-shift workers, and so on."

With its capacity for future projections, the tool may help planners visualize which sections of a city benefit (or lose out) from a given change.