Environment

Auto Added by WPeMatico

Using machine learning to help people make smart decisions about solar energy

Using machine learning to help people make smart decisions about solar energy

 A few years ago, when my family was first deciding whether or not to go solar, I remember driving around the neighborhood, looking at all the solar arrays on nearby rooftops. It made me realize: Wow, solar isn’t some futuristic concept, it’s already part of the fabric of my town! Seeing that others around me were already benefiting from solar helped me decide to do the same.

We want to make it easy for people to make informed decisions about whether to invest in solar. Project Sunroof already shows you solar potential and cost saving for more than 60 million individual homes. Today we’re adding a new feature, Project Sunroof Data Explorer, which shows a map of existing solar installations in neighborhoods throughout the United States. Now instead of driving street to street, it’s a little easier to see if houses around you and communities nearby have already gone solar.  

one
Click on “existing arrays” in the upper right corner to see number of existing installations in your region

This feature combines machine learning with imagery from Google Maps and Google Earth to provide an estimate of how many houses in an area have solar. We started by taking in high-resolution imagery of rooftops and manually identifying solar installations. We then used that data as the initial training set for our algorithm. After many iterations, our machine learning algorithms can now automatically find and identify installations in the imagery (both photovoltaic panels, which produce electricity, and solar hot water heaters). Even for machines, practice makes perfect!

2

So far we’ve identified around 700,000 installations in the U.S. and over time, as we continue to train the algorithms and apply improvements, we will be able to find and show more installations. We hope that this new feature will provides policy makers, communities and individuals with more information to help make smarter decisions in their transition to cleaner power sources.

Go to Source

Posted by amiller in Blog, Environment, Google Earth, Maps
Let’s clear the air: mapping our environment for our health

Let’s clear the air: mapping our environment for our health

How hot will it be today? What is the traffic for my commute to work? Where’s the nearest grocery store? Every day we use data about the world around us to make decisions. One useful dataset is air pollution data, which contains much-needed information that can help us understand how to live healthier lives, build smarter and more sustainable cities, and reduce climate-changing greenhouse gases in both urban and rural areas.

Mapping air pollution at street level

Today, with our partners at Environmental Defense Fund (EDF) and Aclima, we’re sharing the first results of an endeavor we started in 2015: to measure air quality using Aclima equipment mounted on Google Street View cars. You can now see maps for Oakland, CA, released by EDF, of nitric oxide (NO), nitrogen dioxide (NO2) and black carbon—pollutants emitted from cars, trucks and other sources that can affect our health and our climate.

airview-blackcarbon1.png
Black carbon particles come from burning fuel, especially diesel, wood and coal. High exposure is associated with heart attacks, stroke and some forms of cancer. Air quality data from Google/Aclima; analysis by Apte et al/EDF. Colors on the map do not correlate to colors on the Air Quality Index.

Zooming in, you can see street-level details that show how pollution can change block by block. For example, the area where the Bay Bridge meets the I-80, a major freeway, has sustained higher pollution levels due to vehicles speeding up to cross under I-80 and merge onto the bridge. These insights can help community groups like the West Oakland Environmental Indicators Project get a better understanding of local air quality and assist regulators like the Bay Area Air Quality Management District in identifying opportunities to achieve greater air quality improvements. This kind of information can also be applied to other cities, who are trying to understand local air quality patterns and implement solutions that improve the local environment.

airview-blackcarbon2.png
Zoom-in of black carbon in Oakland, where you can see block-by-block air quality. Air quality data from Google/Aclima; analysis by Apte et al/EDF. Colors on the map do not correlate to colors on the Air Quality Index.

We hope Bay Area residents use this resource to explore air quality in Oakland, and find out how you can do your part to improve it. Scientists can request access to the validated data now. You can also learn more about the science behind these maps in the journal Environmental Science & Technology, authored by a scientific team led by Dr. Joshua Apte, at the University of Texas-Austin.

Today’s news follows our 2014 project with EDF to map methane leaks, and our 2015 announcement with Aclima to map air quality in Los Angeles, San Francisco and the Central Valley communities. We’re excited to share the data that made this science possible with more researchers.

With nearly 3 million measurements and 14,000 miles captured in the course of a year, this is one of the largest air quality datasets ever published, and demonstrates the potential of  neighborhood-level air quality mapping. This map makes the invisible, visible, so that we can breathe better and live healthier. It helps us understand how clean (or not clean) our air is, so that we can make changes to improve it.

Go to Source

Posted by amiller in Blog, Environment, Maps
Partnering with E.ON to bring Project Sunroof to Germany

Partnering with E.ON to bring Project Sunroof to Germany

Solar power is an abundant, low-carbon source of electricity, but historically it’s been more expensive than traditional electricity. Now, with solar costs dropping dramatically, many people are starting to ask: Does solar power make sense on my roof?

We launched Project Sunroof in the United States in 2015 to help answer this question and help consumers make accurate decisions about solar power for their homes. Starting today, people in Germany will be able to see the solar potential of their rooftops thanks to a partnership between Project Sunroof, E.ON and the software producer Tetraeder. This marks the first time Project Sunroof data will be made available outside of the U.S.

Around 7 million German buildings are currently covered by Project Sunroof, including urban areas such as Munich, Berlin, Rhine-Main and the Ruhr area. It’s as easy as entering your address.

To estimate the solar potential for individual buildings, we combined Google Earth, Google Maps, 3D models and machine learning to estimate solar generation potential accurately and at large scale. Project Sunroof estimates how much sunlight falls on the roof, accounting for historical weather patterns, the location of the sun throughout the year, the geometry of the roof, and shading from nearby objects such as trees and buildings. We then combine all of these factors to estimate solar energy generation potential for a particular address.

Project Sunroof DE

Project Sunroof data will be integrated on www.eon-solar.de beginning today. On the site, people can investigate their home’s solar potential, as well as purchase a suitable system consisting of photovoltaic modules, energy storage and system management software provided by E.ON. As of this month, the online tool covers about 40 percent of German homes.

Google has been using renewable energy sources within our own infrastructure and beyond for many years—in 2017, we announced a commitment for 100 percent renewable energy across our operations worldwide. With Project Sunroof, we want to help people become even more aware of the solar potential that’s just above the rafters. The future is bright!

Go to Source

Posted by amiller in Blog, Environment, Google in Europe, renewable energy, solar energy, google germany, google renewable energy, project sunroof, solar panels
Shedding light on solar potential in all 50 U.S. States

Shedding light on solar potential in all 50 U.S. States

Solar power is an abundant, low carbon source of electricity, but historically it has been more expensive than traditional electricity. With solar costs dropping dramatically, many people are starting to ask: does solar power make sense on my rooftop? In my town or state?  Since its initial launch in 2015, Project Sunroof has used imagery from Google Maps and Google Earth, 3D modeling and machine learning to help answer those questions accurately and at scale. For every building included in the data, Project Sunroof calculates the amount of sunlight received by each portion of the roof over the course of a year, taking into account weather patterns, position of the sun in the sky at different times of year, and shade from nearby obstructions like trees and tall buildings. Finally, the estimated sunlight is translated into energy production using industry standard models for solar installation performance.

Project Sunroof county-level coverage from 2015 – 2017

Today, Project Sunroof is helping answer those questions for more places than ever, with an expansion that brings Project Sunroof’s data coverage to every state in the U.S, with a total of approximately 60 million buildings analyzed. The expanded data reveals some fascinating insights about the solar energy opportunity nationwide:Seventy-nine percent of all rooftops analyzed are technically viable for solar, meaning those rooftops have enough unshaded area for solar panels.Over 90 percent of homes in Hawaii, Arizona, Nevada and New Mexico are technically viable, while states like Pennsylvania, Maine and Minnesota reach just above 60 percent viability. Houston, TX has the most solar potential of any U.S. city in the Project Sunroof data, with an estimated 18,940 gigawatt-hours (GWh) of rooftop solar generation potential per year. Los Angeles, Phoenix, San Antonio, and New York follow Houston for the top 5 solar potential cities — see the full top 10 list in the chart below.

To put the rooftop solar potential into perspective, the average U.S. home consumes 10,812 kilowatt-hours (kWh) a year according to EIA. There are one million kWh in one gigawatt-hour (GWh). One GWh of energy is enough to supply power to 90 homes for an entire year.

If the top ten cities above reached their full rooftop solar potential, they’d produce enough energy to power 8 million homes across the US.

Sample of Project Sunroof solar energy potential map

This also means that if you’ve been thinking about going solar, there’s a much better chance there’s Project Sunroof data for your area. The Project Sunroof data explorer tool allows anyone to explore rooftop solar potential across U.S. zip codes, cities, counties and states. If you’re looking to learn about the solar and financial savings potential for your homes, the Project Sunroof savings estimator tool now covers 40x more buildings in the U.S. than when we launched it in 2015.

Visualization of solar potential at the Googleplex in Mountain View, CA.

Almost 10 years ago, Google became an early adopter of rooftop solar, installing a 1.6 megawatt (MW) solar array at our headquarters in Mountain View, CA—the largest corporate solar installation of its kind at the time. Today, Project Sunroof combines Google’s longstanding interest in sustainability and renewable energy with unique, high-quality information about the potential of rooftop solar power. We’re proud to be expanding coverage of this project to help more people decide if solar makes sense for you.  

Powered by WPeMatico

Posted by amiller in Blog, Environment, Google Earth, Maps