Updating the Artificial Chemist | AIChE

Updating the Artificial Chemist


The August 2020 issue of CEP covered a novel artificial intelligence (AI) platform from North Carolina State Univ. (NCSU) that can automatically run and optimize chemical reactions (“Artificial Chemist Platform Advances R&D,” pp. 10–11), which could help accelerate materials development. Now, the NCSU team has made a few improvements to the unique system, dubbed the Artificial Chemist.

The platform can run numerous experiments under different conditions. As these experiments are rapidly conducted, the AI “brain” quickly learns, using data it collects to inform subsequent experiments. Like a human chemist, it runs experiments to understand the reaction model, and after 10–15 experiments, it has enough data to design the target material. Previously, the NCSU team used the Artificial Chemist to produce perovskite quantum dots (QDs), which are useful in light-emitting diode (LED) technology.

Through repeated experiments, the system learned which conditions would best improve the properties of the QD. However, the Artificial Chemist’s autonomous decision-making mechanism that chooses the conditions of each experiment will need to be customized for every application.

In other words, the optimal mechanism is different for every material. In...

Would you like to access the complete CEP News Update?

No problem. You just have to complete the following steps.

You have completed 0 of 2 steps.

  1. Log in

    You must be logged in to view this content. Log in now.

  2. AIChE Membership

    You must be an AIChE member to view this article. Join now.

Copyright Permissions 

Would you like to reuse content from CEP Magazine? It’s easy to request permission to reuse content. Simply click here to connect instantly to licensing services, where you can choose from a list of options regarding how you would like to reuse the desired content and complete the transaction.