- A new initiative by non-profits WattTime, the Carbon Tracker Initiative and the World Resources Institute (WRI) will use artificial intelligence and satellite technology to quantify the emissions from every large power plant around the world.
- The project is backed by a £1.7m grant from Google’s AI Impact Challenge, which issued an open call to organizations around the world to submit their ideas for how they could use AI to help address societal challenges.
The project will work by leveraging the growing global satellite network that surrounds the earth to observe power plants from space. AI technology will use the latest image processing algorithms to detect signs of emissions from power plants.
The algorithms will look at a whole range of different indicators of power plant emissions, from thermal infrared images, which indicate heat near smokestacks and cooling water intake, to visual spectrum recognition, which sounds complicated but simply means that satellites are looking for signs that a power plant is emitting smoke.
This information will then be analysed by artificial intelligence software that will grow smarter and more capable over time. For example, initial analysis might measure overall levels of pollution from each power plant, while future versions could break down pollution into its separate parts, identifying carbon, methane, particulate matter, and more.
The data findings will be made publicly available, so citizens can then use the information to call on politicians and companies to reduce emissions.
The initiative aims to keep governments and big polluting energy companies honest and man up to their carbon emissions commitments and legal responsibilities.
Author: Bryan Groenendaal