The project, developed by nonprofit emissions reduction software company Watt Time, will use a global network of satellites to measure carbon dioxide emissionsand then make the data public.
It is backed by Google’s philanthropic wing, Google.org which has provided a $1.7m (£1.34m) grant.
Watt Time’s stated aim is “to use the resulting data both to hold polluting plants accountable to environmental standards, as well as to enable advanced new emissions reduction technologies.”
The company will work alongside other nonprofit companies to interpret, use and publish the data.
“Far too many power companies worldwide currently shroud their pollution in secrecy. But through the growing power of artificial intelligence (AI), our little coalition of nonprofits is about to lift that veil all over the world, all at once,” said Gavin McCormick, the firm's executive director.
“To think that today a little team like ours can use emerging AI remote sensing techniques to hold every powerful polluter worldwide accountable is pretty incredible. But what I really love about better data is how it puts most companies, governments, and environmentalists on the same side. We’ve been thrilled to see how many responsible, forward-thinking groups have started using advanced data to voluntarily slash emissions without anyone making them.”
The system promises far greater accuracy and detailed emissions data for each power station, effectively reducing barriers to insight into the impacts of power generation, ensure accurate emissions data and bring new opportunities to hold companies to account.
The satellite network will observe the power plants from space, while AI technology will use the image processing algorithms to detect signs of power plant emissions.
The project will ultimately combine data from a variety of different sensors. AI algorithms will cross-validate various indicators of power plant emissions. This will include using thermal infrared measurements to detect heat near smoke stacks or cooling water intake, and also using visual spectrum recognition technology to observe whether a power plant is emitting smoke.
Jacquelline Fuller, president of Google.org said: “AI is at a nascent stage when it comes to the value it can have for the social impact sector, and we look forward to seeing the outcomes of this work and considering where there is potential for us to do even more.”
Watt Time’s previous work includes a system in operation in the US called Automated Emissions Reduction (AER), which uses grid data alongside constantly learning algorithms to assess when the grid is running on the cleanest forms of energy. Houses with smart devices can then automatically adjust to take advantage of the available power.
The new satellite system provides the future possibility for an AER-type system to be rolled out across the globe.
More about: Earth