AI helps capture more CO2 with less energy

Researchers at the University of Surrey used artificial intelligence to adjust a system based on a real coal-fired power station and capture 16.7% more carbon dioxide (CO2) while using 36.3% less energy from the UK National Grid.   

“Usually, carbon capture systems run constantly, at the same rate – regardless of the externally changing environment. But we showed that teaching the system to keep making small adaptations can produce big energy savings – and capture more carbon at the same time,” Jin Xuan, chair of sustainable processes at the University of Surrey’s School of Chemistry and Chemical Engineering, said in a media statement.

Xuan explained that the CO2 that power plants produce when they burn fuel can be captured by bubbling the flue gas through water containing limestone. CO2 reacts with the calcium carbonate in the limestone and this produces harmless bicarbonate, in a process known as “enhanced weathering.”

The CO2 capture plant that Xuan and his team worked with had its own wind turbine, however, in calmer weather, it took energy from the grid to pump both the water and the greenhouse gas.

Using AI, the researchers taught a model system to predict what would happen – so it could pump less water when there was less CO2 to capture, or when less renewable energy was available.   

The team hopes their findings can be used more widely throughout the industry, contributing towards United Nations Sustainability Goals.

“Although we tested our model on enhanced weathering, the principles apply more widely. Our model could help anybody trying to capture and store more CO2 with less energy – whatever the process they’re using,” said Lei Xing, lecturer in chemistry and chemical engineering at the University of Surrey and co-author of the Reaction & Chemistry Engineering paper that presents the findings.