A nonprofit artificial intelligence firm called WattTime will soon enable us to efficiently track worldwide power plant emissions. The initiative takes advantage of the increased availability of satellite imagery and explosive improvements in machine learning technology to build a kind of smart eye-in-the-sky.
Between visible smoke, heat, and NO2, WattTime will be able to derive exact, real-time emissions information, including information on carbon emissions, for every power plant in the world. (McCormick says the data may also be used to derive information about water pollutants like nitrates or mercury.)
We’ll soon know the exact air pollution from every power plant in the world. That’s huge.
Other examples of organizations using machine-learning to enhance satellite imagery include Global Forest Watch, which focuses on protecting the world’s forests, and Project Skylight, which monitors global fishing practices. These initiatives are part of an even broader movement of using machine learning to solve a broad range of societal and ecological challenges—sometimes referred to as “AI4Good.”
Thank you Gideon
Another one:
Laser-carrying drones that can see through the forest canopy are being used to protect native Scottish plants threatened by invasive species.
The drones use Lidar (light detection and ranging), which works like radar but uses light instead of radio waves.
Laser pulses are fired at the trees below and the time it takes for wavelengths to bounce back is used to create a 3D picture of what lies beneath.
The data is combined with information from satellites to give an accurate “fix” of the drone’s position.
It all builds up an accurate map of the health of the forest floor.
https://www.bbc.com/news/amp/uk-scotland-48380213
South Africa’s coal fired power stations will show why we rank so poorly for pollution.
Having that kind of transparency could be very helpful. I keep forgetting that you live in South Africa.