My Google Map Blog

Cities bring people and ideas together. They increase living standards, spur innovation, increase opportunity, and encourage collaboration. Cities can also be the most environmentally sustainable way for people to inhabit our planet, if we can address the reality that cities are currently responsible for 70 percent of the world’s CO₂ emissions. While this may seem like an insurmountable challenge, it’s actually a tremendous opportunity. Cities can become centers of climate action, and lead the world in driving economic recovery and resilience. 

As part of Google's most ambitious decade of climate action, we’re making a commitment to help more than 500 cities and local governments reduce an aggregate of 1 gigaton (that’s one billion tons) of carbon emissions per year by 2030 and beyond.

To do this, we'll empower city planners and policymakers with the Environmental Insights Explorer (EIE), a platform we developed by analyzing Google’s comprehensive global mapping data together with standard greenhouse gas (GHG) emission factors. Today, we’re expanding access to EIE, going from 122 cities with access to more than 3,000 cities worldwide—a 25-fold increase. We’re also partnering with leading organizations, like ICLEI and Ironbark Sustainability, to support local climate action planning.

Turning climate insights into action

For cities to make a meaningful impact in reducing their carbon emissions tomorrow, they need to know where they stand today.

Yet according to the Global Covenant of Mayors, an international alliance of nearly 10,000 cities and local governments committed to fighting climate change, less than 20 percent of cities are able to execute on their commitments to climate action due to a lack of time, resources and data. And with COVID-19 leaving many localities with reduced budgets and limited resources, it’s even harder to build out a baseline emissions inventory or a robust climate plan.

With Environmental Insights Explorer, cities can leapfrog the constraints associated with lengthy climate studies. Cities can use EIE’s anonymized, aggregated mapping data and emissions insights to easily estimate the carbon footprint of their buildings and transportation activities, as well as discover their solar energy potential. Information that once required complicated onsite measurements and months to compile can now be assessed virtually, helping cities dedicate their energies toward action.

Cultivating partnerships with climate action leaders and cities worldwide

When it comes to climate change, we all need to work together. Nonprofits, businesses, universities and other leaders play an important role in testing new ideas and partnering with cities to implement the ones that work.

We’ve collaborated with partners to scale data access. Leading organizations like Local Governments for Sustainability (ICLEI ) and Ironbark Sustainability are integrating EIE data into their own tools, helping digitize emissions measurement and planning. With EIE data, Ironbark Sustainability is automating how they provide greenhouse gas emission information to local government councils across Australia so decision-makers can target their climate action activities.

To help spark even more data-driven climate action, last year Google.org committed $4 million in funding to ICLEI Local Governments for Sustainability to create the ICLEI Action Fund. The fund awards projects from local organizations in Europe, Mexico and South America focused on using environmental datasets to reduce citywide emissions.

Today, ICLEI is announcing the first two selected projects. In Hamburg, HafenCity University is creating a tool to help the city identify spaces and districts that can be used as urban testbeds for prototyping sustainable mobility, building efficiency and solar energy development projects. In Monterrey, Mexico, Instituto Tecnológico de Monterrey received a grant to refine and amplify EIE data to help municipalities in the Monterrey region develop climate action plans. They’ll also use the data to run a model of traffic patterns in Monterrey to assess the electrification of a fleet of buses and how to optimize  transit routes.  

Supporting economic recovery and resilience with climate action

Efforts to combat climate change are both essential and a once-in-a-generation moment to create impactful jobs and modernize infrastructure. As communities are working to combat, and recover from, a global pandemic, reducing carbon emissions can and should support that recovery. 

Already, cities and local governments across the world are using EIE to set bold climate action plans and support economic development:

The opportunity in front of us all

We’ve always viewed challenges as opportunities to be helpful and make things better for everyone. To build a better future and protect our planet, we’ll continue focused efforts that help our partners take climate action and strengthen investments in technologies to make a carbon-free world a reality.

Every day, over 1 billion kilometers are driven with Google Maps in more than 220 countries and territories around the world. When you hop in your car or on your motorbike and start navigating, you’re instantly shown a few things: which way to go, whether the traffic along your route is heavy or light, an estimated travel time, and an estimated time of arrival (ETA). While all of this appears simple, there’s a ton going on behind the scenes to deliver this information in a matter of seconds.

Today, we’ll break down one of our favorite topics: traffic and routing. If you’ve ever wondered just how Google Maps knows when there’s a massive traffic jam or how we determine the best route for a trip, read on. 

Live traffic, powered by drivers all around the world

When people navigate with Google Maps, aggregate location data can be used to understand traffic conditions on roads all over the world. But while this information helps you find current traffic estimates —whether or not a traffic jam will affect your drive right now—it doesn’t account for what traffic will look like 10, 20, or even 50 minutes into your journey. This is where technology really comes into play.

Predicting traffic with advanced machine learning techniques, and a little bit of history

To predict what traffic will look like in the near future, Google Maps analyzes historical traffic patterns for roads over time. For example, one pattern may show that the 280 freeway in Northern California typically has vehicles traveling at a speed of 65mph between 6-7am, but only at 15-20mph in the late afternoon. We then combine this database of historical traffic patterns with live traffic conditions, using machine learning to generate predictions based on both sets of data. 

Recently, we partnered with DeepMind, an Alphabet AI research lab, to improve the accuracy of our traffic prediction capabilities. Our ETA predictions already have a very high accuracy bar–in fact, we see that our predictions have been consistently accurate for over 97% of trips. By partnering with DeepMind, we’ve been able to cut the percentage of inaccurate ETAs even further by using a machine learning architecture known as Graph Neural Networks–with significant improvements in places like Berlin, Jakarta, São Paulo, Sydney, Tokyo, and Washington D.C. This technique is what enables Google Maps to better predict whether or not you’ll be affected by a slowdown that may not have even started yet! 

Keeping it fresh

For most of the 13 years that Google Maps has provided traffic data, historical traffic patterns have been reliable indicators of what your conditions on the road could look like—but that's not always the case. Since the start of the COVID-19 pandemic, traffic patterns around the globe have shifted dramatically. We saw up to a 50 percent decrease in worldwide traffic when lockdowns started in early 2020. Since then, parts of the world have reopened gradually, while others maintain restrictions. To account for this sudden change, we’ve recently updated our models to become more agile—automatically prioritizing historical traffic patterns from the last two to four weeks, and deprioritizing patterns from any time before that.

How Google Maps selects routes

Our predictive traffic models are also a key part of how Google Maps determines driving routes. If we predict that traffic is likely to become heavy in one direction, we’ll automatically find you a lower-traffic alternative. We also look at a number of other factors, like road quality. Is the road paved or unpaved, or covered in gravel, dirt or mud? Elements like these can make a road difficult to drive down, and we’re less likely to recommend this road as part of your route. We also look at the size and directness of a road—driving down a highway is often more efficient than taking a smaller road with multiple stops.

Two other sources of information are important to making sure we recommend the best routes: authoritative data from local governments and real-time feedback from users. Authoritative data lets Google Maps know about speed limits, tolls, or if certain roads are restricted due to things like construction or COVID-19. And incident reports from drivers let Google Maps quickly show if a road or lane is closed, if there’s construction nearby, or if there’s a disabled vehicle or an object on the road. Both sources are also used to help us understand when road conditions change unexpectedly due to mudslides, snowstorms, or other forces of nature.

Putting it all together

So how exactly does this all work in real life? Say you’re heading to a doctor’s appointment across town, driving down the road you typically take to get there. When you leave the house, traffic is flowing freely, with zero indication of any disruptions along the way. With Google Maps’ traffic predictions combined with live traffic conditions, we let you know that if you continue down your current route, there’s a good chance you’ll get stuck in unexpected gridlock traffic about 30 minutes into your ride—which would mean missing your appointment. As a result, Google Maps automatically reroutes you using its knowledge about nearby road conditions and incidents—helping you avoid the jam altogether and get to your appointment on time.

Predicting traffic and determining routes is incredibly complex—and we'll keep working on tools and technology to keep you out of gridlock, and on a route that's as safe and efficient as possible.

What kind of places are people saving? To give you a sense, here’s a selection of the all-time most popular places and recent rising categories:

Today, we’re starting to rollout updates to the Saved tab that will make it even easier for you to find and remember the places that matter most to you. Here are three tips for the new Saved tab:

1. Remember your most recently saved places

When you’ve saved a place a friend or colleague recommended and a few days or weeks have passed, it can be hard to remember what the name of the place was or what list you even saved it to. Now, your recently saved places are organized at the top of the Saved tab so you can quickly find the place you’re looking for.

When you have a lot of saved places in your current area, it can be challenging to quickly figure out which is which and where to go. When location permission is enabled, you can see all your nearby saved places sorted by distance and arranged in a carousel for easy browsing to make your next decision a breeze.

If you’ve chosen to turn on your Location History setting, you can use your Timeline to remember the places you’ve been and routes you’ve taken. You can see how far you’ve biked, walked and ran over the past few days. You can also easily find that amazing hole in the wall restaurant you visited during one of your past vacations, or that cute boutique you popped into a few weeks ago. All of these insights are now organized by time, city, region or country.

Ten years ago, I was inside the Google office in Haifa, Israel when the devastating Carmel Mountain fire started blazing not far from us. The team started searching the web to learn more. And while we did find some details confirming what we already knew—a large fire was taking place outside of our door—we experienced a potentially life-impacting information gap. 

This kick-started our journey to build features in Google Search and other products that connect people with high-quality information during crises. A few hours after I took the photo below, we quickly launched a small feature in Search that made it easier for people to find the emergency hotline for the Carmel Mountain fire. Since then, we’ve continued to evolve and expand off this initial launch into the SOS alerts we launched in 2017.

Connecting people to critical information during active wildfires

Today we’re launching a new wildfire boundary map in Search and Maps SOS alerts in the U.S. to provide deeper insights for areas impacted by an ongoing wildfire. In moments like a growing wildfire, knowing exactly where a blaze is underway and how to avoid it is critical. Using satellite data to create a wildfire boundary map, people will now see the approximate size and location right on their phone or desktop. 

When people look for a specific fire like "Pine Gulch fire" or “Apple fire” in Search, they will be able to see a wildfire’s approximate boundary of the fire, name and location, as well as news articles and helpful resources from local emergency agencies in the SOS alert. 

On Google Maps, people will have access to the same details, including the fire boundary, and receive warnings if they’re approaching an active blaze. If someone is exploring an area near a wildfire on Google Maps, they’ll get an ambient alert that will point them to the latest information.

How we map fires to help keep people safe 

From there, we create a digital polygon—the red boundary shown on the map in Search and Google Maps—that represents the approximate wildfire impact area. If multiple large fires are active in the same region, people may see several polygons. You can learn more about how we gather, analyze and visualize wildfire data from satellites on our Medium blog.

Putting this information to work 

This year the National Interagency Fire Center has predicted above normal fire risks for several areas across the U.S. Already, firefighters have confronted large blazes across Northern and Southern California, as well as the Grizzly Creek Fire in Colorado, which led to evacuations and burned thousands of acres. In these situations, having high-quality information at your fingertips matters.

For example, in the recent Apple, Pine Gulch, and Grizzly fires, we quickly identified that the wildfires were rapidly expanding, and dry conditions exacerbated the fire, putting thousands of people at risk. We were able to launch our SOS alerts, with the latest boundary map, on Search and Google Maps.

Last year, we piloted this feature in Search for major California wildfires to confirm it was a useful tool for first responders, emergency management personnel and the community. We collaborated with organizations, like the California Governor's Office of Emergency Services (Cal OES) and Boulder’s Office of Emergency Management, to gather expert recommendations on wildfire preparedness and response. Their feedback throughout our 2019 pilot helped identify what information is most useful during emergency situations.

Google has been involved in crisis response for many years, starting with the Carmel Mountain Fire in Israel in 2010. Since then, we've initiated Public and SOS alerts for hundreds of thousands of crises around the world. From wildfire mapping, to earthquake detection and alerts to flood forecasting, we continue to find new ways for technology to be helpful at the most critical times.

Since it launched 15 years ago, Google Maps has redefined what it means to be a map–evolving from a powerful navigational tool to a robust daily companion that also offers helpful information about where to go and what to do. Features like popular times, multimodal navigation, and offline maps help you better understand your world so you can decide how to interact with it.

This week, we’re rolling out new visual improvements that bring even more detail and granularity to the map, making it easier to understand what an area looks like whether you’re exploring virtually or planning a visit.

A more colorful and accurate view of the world