AI-Enhanced Carbon Capture for Climate-Friendly Power Plants

According to a University of Surrey study, carbon capture maybe even more climate-friendly.  Scientists modified a coal-fired power plant-based system by utilizing artificial intelligence (AI). The model could reduce energy consumption from the National Grid by 36.3% while capturing 16.7% more carbon dioxide (CO₂).

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, Professor and Associate Dean, Research and Innovation, University of Surrey

A greenhouse gas called CO₂ is produced when fuel is burned in power plants. However, it can be collected by passing the flue gas through limestone-infused water as it bubbles. The limestone's calcium carbonate and CO₂ interact. This results in "enhanced weathering," which yields innocuous bicarbonate.

It needs energy to pump the water and the CO₂. Although the CO₂ collection plant had a wind turbine of its own, it used grid power during calmer periods.

A model system was trained to anticipate future events using artificial intelligence (AI). This allowed the system to reduce water pumping during periods of reduced CO₂ capture or renewable energy availability. The group hopes that making their findings more publicly available in the business will help achieve UN Sustainability Goals 7,9,12, and 13.

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 are using.

Dr. Lei Xing, Lecturer, Digital Chemical Engineering, University of Surrey

Dr Lei Xing is also a Fellow of the Institute for Sustainability and a Fellow of the Institute for People-Centred Al.

Journal Reference:

Fisher, O. J., et.al., (2023). Responsive CO₂ capture: predictive multi-objective optimisation for managing intermittent flue gas and renewable energy supply. Reaction Chemistry & Engineering. doi.org/10.1039/D3RE00544E.

Source: https://www.surrey.ac.uk/