Researchers from North Carolina State University and the University at Buffalo have developed a new AI-based solution to speed up expected results in chemical experiments.
The technology, called “Artificial Chemist”, is an artificial intelligence-based solution, able to identify and produce the best possible material for a specific application. This virtual helper takes properties from scientists and delivers results that match scientists’ expectations. It was first developed to help manufacturing of quantum dots, which are colloidal semiconductor nanocrystals typically used in LED displays. Scientists say that the Artificial Chemist is similar to a self-driving car. It sees the destination and find the optimal route to it completely by itself. For their initial testing scientists experimented with nanocrystals. "Artificial Chemist is a truly autonomous system that can intelligently navigate through the chemical universe," says Milad Abolhasani, corresponding author of a paper on the work and an assistant professor of chemical and biomolecular engineering at NC State.
The Artificial Chemist has both a "body" for performing experiments and sensing the experimental results, and a "brain" for recording that data and using it to determine what the next experiment will be. At this time, the Artificial Chemist, which is acting as a smart tool, could run 500 quantum dot synthesis experiments per day but it is learning at the same time and can find a shorter way to achieve the proposed goal. This is why now, based on its augmented knowledge, it could identify the optimal material for new properties in 10 to 15 minutes.