Stories

Driving a Sustainable Future: How Google’s Transportation Solutions are Helping Transform Mobility in Brazil

November 2025

Featured Technology

Google Maps Platform

Fuel-efficient routing (FER)

Green Light

Alternative route suggestions

Environmental Insights Explorer (EIE)

Who We’re Helping

Cities and local governments, such as Rio de Janeiro, Campo Grande, São Paulo, Brasília, and individual Brazilians—drivers, commuters, pedestrians, and transit users.

Our Role

Google provides innovative AI and geospatial data tools that enable cities and individuals to make more sustainable transportation decisions. This includes optimizing routes, reducing traffic, and promoting cleaner travel options, leading to savings in fuel, time, and carbon emissions.

The new Rio Branco Avenue in Rio

For more than a decade, Google has been using AI to tackle some of the world’s most pressing environmental challenges, including one of the largest sources of emissions: transportation. This commitment is realized through our innovative mobility tools that make commuting easier and more efficient, leading to savings in time and fuel, and ultimately contributing to reduced emissions and lower individual transportation costs.

A prime example of how our transportation solutions can make a positive impact is in Brazil. For years, we've partnered with local governments—from megacities like São Paulo to tree-lined Campo Grande—to roll out a suite of AI-powered tools including fuel-efficient routing in Google Maps, Green Light, and Environmental Insights Explorer. Together, we’re empowering millions of residents to choose modes of travel that are more efficient, saving them time and money while simultaneously reducing fuel consumption and decreasing greenhouse gas emissions.

Rio de Janeiro: Tackling Traffic, Reducing Emissions

Rio de Janeiro is at the forefront of this effort, being one of the first cities in the world to test Green Light, one of Google’s groundbreaking transportation innovations. By using AI to optimize traffic light timing at specific intersections, Green Light helps drivers limit unnecessary stops, smoothing traffic flow and cutting fuel consumption and associated emissions.

In 2023, Rio began implementing the solution to tackle the persistent challenge of stop-and-go traffic, and Green Light has now expanded to three cities in Brazil. The positive impact is already clear: In September 2025, we estimate that Green Light reduced stops by approximately 9% and fuel usage by approximately 15% at 83 intersections around the country, enabling an estimated 100 metric tons of greenhouse gas emissions reductions per month.1

Campo Grande: Using Data for Urban Planning

In Campo Grande, the focus is on a different kind of innovation: using data to inform policy. The city leverages Google’s Environmental Insights Explorer (EIE) to gain a critical understanding of its emissions landscape.

EIE analyzes local transportation patterns to determine climate action strategies such as "gerenciamento inteligente de tráfego" (intelligent traffic management), which helps city planners design infrastructure that prioritizes non-motorized travel and public transit access. This partnership and EIE’s years of transportation data allowed Campo Grande to not only set clear targets, including to reduce CO2 emissions by at least 5% and average travel time by 15% on main corridors by 2026, but to also monitor progress toward these goals. And Campo Grande isn’t the only city leveraging this data. In fact, our momentum in Brazil is strong! We've successfully partnered with 108 cities, well exceeding our goal of 100 Brazilian city partnerships. This includes key locations like São Luís, MA; Teresina, PI; Volta Redonda, RJ; and Boa Vista, RR.

São Paulo, Brasília, and More: Encouraging CO2-Reducing Commutes

Beyond large-scale city planning, an every day feature like alternative route suggestions in Google Maps is empowering individuals in big cities like São Paulo, Rio de Janeiro, Belo Horizonte, and Brasília to make small, consistent changes that lead to substantial collective impact.

The feature shows options for walking or taking public transportation when these modes are just as fast, if not faster, and are more cost-effective than driving. In September 2025, we estimate that alternative route suggestions empowered people in Brazil to shift over 188,000 trips from driving to more fuel-efficient options.2 These four cities are just the beginning, with plans for more Brazilian locations to see alternative route suggestions in Google Maps in the near future.

A Nationwide Move Toward Efficiency

These city-specific initiatives are part of a broader, country-wide transformation. The nationwide rollout of Google’s fuel-efficient routing has helped drivers across Brazil choose more fuel-conscious routes using sophisticated machine learning. In September 2025, 45 million users in Brazil took a fuel-efficient route, which we estimate saved 2.1 million liters of fuel, reducing an estimated 4,000 metric tons of greenhouse gas emissions.3

We carefully measure our products to understand how we're making a positive impact. We use real-world signals and third-party data to estimate the enabled greenhouse gas emission reductions, and we’ve detailed our methodology in our enabled emissions reduction principles, published in early 2025.

Throughout Brazil and around the world, we see that these cutting-edge tools emphasize how even small, consistent changes can lead to a collective impact. Their positive effects are being observed in real-time, delivering tangible benefits across multiple scales: for individuals seeking more efficient commutes, for cities striving for sustainable urban development, and for the planet in the critical fight against climate change.

To learn more about our measurement principles, read the enabled emissions reduction principles here.

By Grant Goodman, Senior Strategy and Operations Lead
Cherry Ying, Strategy and Operations Associate
Yasha Wallin, Marketing Manager
Jackie Mauro, Data Scientist

1 Emissions reductions estimates are modeled using a U.S. Department of Energy emissions model. A single fuel-based vehicle type is used as an approximation for all traffic, adjusted for country-level fleet mix from IEA data. To estimate fuel savings at an intersection, we first estimate the number of cars passing through an intersection, as well as the behavior: stopping, slowing, turning, etc. Using this in combination with the emissions model, Google can estimate the fuel emitted at each intersection. For a sample of intersections in Brazil, Google analyzed traffic patterns before and after recommended adjustments to traffic signals that were implemented. Based on results of the pre-post analysis, we extrapolated to the rest of Brazil’s intervention. Enabled emissions reductions estimates include inherent uncertainty due to factors that include the lack of primary data and precise information about real-world actions and their effects. These factors contribute to a range of possible outcomes, within which we report a central value. The data and claims have not been verified by an independent third-party.

2 We count trips shifted away from driving if a user initially requests driving directions, is prompted with our suggestion and then presses “Start Navigation” in either walk or transit mode.

3 Google uses an AI prediction model, built on top of a U.S. Department of Energy emissions model, to estimate the expected fuel or energy consumption for each route option when users request driving directions. We identify the route that we predict will consume the least amount of fuel or energy. If this route is not already the fastest one and it offers meaningful energy and fuel savings with only a small increase in driving time, we recommend it to the user. To calculate enabled emissions reductions, we tally the fuel usage from the chosen fuel-efficient routes and subtract it from the predicted fuel consumption that would have occurred on the fastest route without fuel-efficient routing and apply adjustments such as: CO2e factors, fleet mix factors, well-to-wheels factors, and powertrain mismatch factors. This figure covers estimated enabled emissions reductions for the month of September 2025 in Brazil. Enabled emissions reductions estimates include inherent uncertainty due to factors that include the lack of primary data and precise information about real-world actions and their effects. These factors contribute to a range of possible outcomes, within which we report a central value. The data and claims have not been verified by an independent third-party.