If you have an ACS member number, please enter it here so we can link this account to your membership. (optional)

ACS values your privacy. By submitting your information, you are gaining access to C&EN and subscribing to our weekly newsletter. We use the information you provide to make your reading experience better, and we will never sell your data to third party members.



Decision-making system makes quantum dots autonomously

Fast-learner becomes more efficient with experience

by Mitch Jacoby
June 21, 2020 | A version of this story appeared in Volume 98, Issue 24

By combining artificial intelligence (AI), machine learning, and microfluidics, researchers have designed an autonomous decision-making synthesis system that chooses optimal reagents, synthetic routes, and reaction conditions to make valuable products with targeted properties. Dubbed “Artificial Chemist,” the system uses tiny quantities of precursors and does not require experienced users to monitor and guide experiment choices. The system, which learns from successive experiments, can reduce the time, cost, and quantity of waste associated with traditional R&D synthesis (Adv. Mater. 2020, DOI: 10.1002/adma.202001626). In a proof-of-concept study, Robert W. Epps and Milad Abolhasani of North Carolina State University and coworkers used the system to make a series of uniform colloidal perovskite quantum dots with preselected emission profiles and other electronic properties. These materials are used in solar cells, light-emitting diodes, and electronic displays. Fitted with syringe pumps, micromixers, and built-in spectroscopy probes, Artificial Chemist reacted cesium lead bromide, zinc halides, and organic capping ligands, then analyzed the products, modified the conditions, and repeated the experiment. The team found that at the outset, the untrained system took about 1.5 h, or 25 experiment runs, to identify optimum synthesis conditions. After the initial run, the system cut the prep time for making new products with other target properties to roughly 15 min.


This article has been sent to the following recipient:

Chemistry matters. Join us to get the news you need.