A few years ago, when my family was deciding whether or not to go solar, I remember driving around the neighborhood, looking at all the solar panels on nearby rooftops. It made me realize: Wow, solar energy is not a futuristic concept, it's already part of the roof of my city! Seeing that others around me were already benefiting from solar energy helped me decide to do the same.
We want to make it easy for people to make informed decisions about investing in solar energy. The Solar Roof Project already shows the solar potential and cost savings of more than 60 million individual homes. Today we are adding a new feature, the Solar Roof Project Data Explorer, which displays a map of existing solar installations in neighborhoods across the United States. Now, instead of driving from street to street, it's a little easier to see if houses around you and nearby communities have already solarized.
This feature combines machine learning with images from Google Maps and Google Earth to provide an estimate of how many houses in an area have solar power. We started by taking high-resolution images of rooftops and manually identifying solar installations. We then use that data as the initial training set for our algorithm. After many iterations, our machine learning algorithms can now automatically find and identify the facilities in the images (both photovoltaic panels, which produce electricity, and solar water heaters). Even for machines, practice makes perfect!
So far we have identified around 700,000 installations in the US and over time, as we continue to train the algorithms and apply improvements, we will be able to find and display more installations. We hope this new feature will provide policymakers, communities, and individuals with more information to help make smarter decisions in their transition to cleaner energy sources.
Request your 100% personalized proposal completely free
quote now
isabel suarez
May 28, 2020