Google's artificial intelligence could be the one who decides which companies should bet on photovoltaic energy on their rooftops. The firm has expanded its Sunroof project to companies and will reach 40 countries, including Spain.
Google Cloud Next introduces three new products for the Google Maps platform that help combat climate change. They all incorporate AI and machine learning, combined with aerial imagery and environmental data, to provide up-to-date information on solar power generation potential, air quality and pollen levels. This technology is available to developers, companies and organizations, to create tools that characterize and mitigate the climate impact on the environment.
With these three new APIs of the Google Maps platform, companies have at their disposal complete and updated environmental information, with which they can develop more sustainable products and help the population adapt to the effects of climate change, according to the search engine.
Having launched the Sunroof tool in 2015 with the aim of promoting the use of solar technologies and helping the public explore the potential of solar energy generation in their area, and the consequent economic savings, Google is expanding to companies.
The new platform, Solar API, uses cartographic and computing resources, and offers detailed data on the potential of solar generation on the roofs of more than 320 million buildings in 40 countries, including Spain, the United States, France or Japan.
To make these calculations, it uses AI to extract 3D information about the geometry of roofs directly from aerial images, also taking into account detailed information about trees and shadows. In addition, API Solar takes into account other factors, such as historical weather series in the area, the cost of energy, etc. As a result, solar panel installers and other businesses can see how much radiation buildings receive and what their energy-saving potential is, before they even visit the area. Likewise, with this technology, homeowners can install solar panels more quickly and easily, and inject sustainable energy into the electricity grid.
Reliable air quality information
Since last year, Google Maps has provided information on air quality, so the public can make better-informed decisions about where to go and what to do. The importance of this situation has made Google present, Air Quality API on the Google Maps platform. The API presents reliable air quality data, pollution heat maps and details on pollutants in more than one hundred countries.
This API is responsible for validating and organizing several terabytes of data every hour, creating an index with local and universal information. The data comes from multiple sources: state monitoring stations, weather data, sensors and satellites. Part of this calculation involves examining real-time traffic information to make sense of data on congestion and vehicle volume in a given area. Like the 'rooftop' map, it uses machine learning to predict what the concentration of different pollutants will be in an area at any given time. Then, companies from various sectors -health, automotive or transport, among others- can transfer the API information to their users.
Common allergen forecasts
Rising temperatures and greenhouse gas emissions also lead to increased proliferation of pollen-producing plants and higher levels of pollen, with consequent adverse effects for allergy sufferers.
Pollen API, the third tool that Google has presented, provides updated information on pollen levels, for the most common causes of allergy, in more than 65 countries. It is also a developer-focused API and provides localized data on the number of pollen particles, views in the form of heat maps, detailed information about pollen-producing plants and practical tips for allergy sufferers to limit their exposure. Again, this data can then be transferred by third parties to their users.
To produce this information with the help of AI, it identifies where certain species of pollen-producing plants are located. This information is combined with local wind patterns, to calculate seasonality and the daily amount of pollen particles, and to predict what pollen propagation will be like.
- Artificial intelligence