Researchers at the University of Toronto Engineering and Carnegie Mellon University are using artificial intelligence (AI) to accelerate progress in transforming waste carbon dioxide (CO2) into commercially valuable product with record efficiency.
The team leveraged AI to speed up the search for the key material in a new catalyst that coverts CO2 into ethylene – a chemical precursor to a wide range of products.
The resulting electrocatalyst is the most efficient in its class. If run using wind or solar power, the system also provides an efficient way to store electricity from the renewable sources.
“Using clean electricity to convert CO2 into ethylene, which has a $60bn global market, can improve the economics of both carbon capture and clean energy storage,” said Professor Ted Sargent, one of the senior authors on the research paper.
Professor Zachary Ulissi of Carnegie Mellon University, commented, “With other chemical reactions, we have large and well-established datasets listing the potential catalyst materials and their properties.”
“With CO2-to-ethylene conversion, we don’t have that, so we can’t use brute force to model everything. Our group has spent a lot of time thinking about creative ways to the most interesting materials.”
The algorithms created by the team use a combination of machine learning models and active learning strategies to broadly predict the types of product a given catalyst is likely to produce, even without detailed modelling of the material itself.
They then applied these algorithms for CO2 reduction to screen over 240 different materials, discovering four promising candidates that were predicted to have desirable properties over a wide range of compositions and surface structures.
In the new paper, the co-authors describe their best-performing catalyst material, an alloy of copper and aluminium. After the two metals were bonded at a high temperature, some of the aluminium was then etched away, resulting in a nanoscale porous structure that Sargent describes as “fluffy.”
The new catalyst was then tested in a device called an electrolyser, where the “faradaic efficiency” — the proportion of electrical current that goes into making the desired product — was measured at 80%, a new record for this reaction.