AI algorithm maps out detailed carbon emissions

A team of Chinese scientists are using artificial intelligence (AI) to map out carbon emissions in big cities. This is an attempt that may help urban managers make more evidence-based plans for fighting global warming.

The experimental tool of researchers from the Aerospace Information Research Institute (AIR) under the Chinese Academy of Sciences is a refitted carbon-monitoring vehicle that regularly monitors bustling zones in Shenzhen.

On a day when the experiment was conducted, a white cylinder rose slowly on top of a van to start sensor-enabled carbon emission monitoring in the city. The carbon monitor measured the road-level concentration of carbon dioxide.

Different from ordinary carbon monitors, the vehicle is equipped with panoramic cameras to capture images of surrounding streets. Data was transmitted to a laboratory at AIR in Beijing, where a brand-new deep learning algorithm is being trained.

Driven by the team’s deep learning algorithm, those cameras could identify carbon emission and sink sources, such as moving cars, buildings, and carbon-fixing vegetation. From there, the AI model can estimate the carbon contributions of those sources.

A 650-kilometer drive has allowed researchers to obtain more than 100,000 street images and data on road traffic carbon emission sources in Shenzhen.

The model is projected to provide a fine guide for city managers, like what causes a certain block to see higher carbon emissions and possible solutions behind it. (Xinhua)