How AI and satellites can help cut emissions

Why are coal plants in the U.S. and Europe closing at an accelerating rate, while in Asia, coal consumption went up and helped fuel an overall 1.7% year-on-year increase in global carbon emissions? 

Part of the reason coal continues to grow in countries like China and India is that in these areas, unlike in the U.S., emissions data can be shoddy or hard to acquire. Without accurate information it is harder to hold facilities accountable and keep them in line with meeting emission reduction targets. 

To address this situation, we are partnering with WattTime and the World Resources Institute (WRI), to launch a new project which will use satellite imagery to quantify carbon emissions from every major power plant across the world. This effort is being funded as one of 20 projects in the Google AI Impact Challenge.  

The project will work by leveraging the growing global satellite network to observe power plants from space. AI technology will use the latest image processing algorithms to detect signs of power plant emissions. 

For maximum accuracy, this work will combine data from a variety of different sensors operating at different wavelengths. AI algorithms will cross-validate multiple indicators of power plant emissions, from thermal infrared, indicating heat near smokestacks and cooling water intake, to visual spectrum recognition that a power plant is emitting smoke.

The new project will build off our pioneering satellite work to use satellite imagery to estimate the utilisation of fossil fuel power plants. Through this initial research we found that 40% of coal power plants in China were losing money and that number could jump to 95% by 2040. 

WattTime will head up the project. They pioneered solutions such as Automated Emissions Reduction techniques, which leverage past, present, and forecasted power grid emissions data and machine learning algorithms. This allows smart devices to adjust the timing of their energy use to sync with clean energy and avoid dirty energy.

In addition, we are working with the WRI, who maintains the most comprehensive Global Database of Power Plants in existence today.

Our ultimate goal is to create a public dataset in the next two years, so users can access emissions data on every power plant. This will give campaigners and researchers, regardless of where they are located, a better picture of global power plant emissions.  The information, which will be available to the public for free, can be used to hold governments and companies accountable around the world, to stricter environmental standards, encourage better emissions reporting, and enable advanced new emissions reduction technologies to be implemented.