In a bid to speed up the search for the key material in a new catalyst, to convert carbon dioxide into ethylene, researchers at Carnegie Mellon University and University of Toronto are using artificial intelligence. The use of the catalyst lies to accelerate the progress of transforming waste carbon into a commercially useful product with record efficiency.
Meanwhile, the resulting electrocatalyst features maximum efficiency in its class. And, if the system is operated using wind or solar energy, it provides an efficient way to store electric energy from these renewable sources.
“The conversion of CO2 into ethylene, which is a US$60 billion worth market, if done using clean energy can improve the economics of carbon capture as well as clean energy storage,” says one of the authors of the research paper published in Nature.
Machine Learning facilitates speeding up search amongst millions of catalysts
Earlier, the team of researchers developed a number of world-leading catalysts to reduce energy cost of the reaction involved to convert CO2 into ethylene and other carbon-based molecules. Nonetheless, there lies probability of availability of better catalysts, but, with a very large number of potential material combinations, testing all of them would involve unacceptable amounts of time.
Machine learning can address this to accelerate the search, says the team. With the help of computer models and theoretical data, algorithms can eliminate worst options and point out towards more promising options.
Earlier, in a workshop organized in 2017, one of the researchers in collaboration with the Canadian Institute for Advanced Research employed AI to advance the search for clean energy materials. Another commentary article published in the Nature later in the year elaborated the idea. The invitees at the workshop included a professor from Carnegie Mellon University whose group specializes in computer modelling of nanomaterials.
