Advertisement

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.

ENJOY UNLIMITED ACCES TO C&EN

Physical Chemistry

Machine learning streamlines electronic structure calculations for molecules

Approach bypasses the most resource-intensive density functional theory equations

by Jyllian Kemsley
October 23, 2017 | A version of this story appeared in Volume 95, Issue 42

A machine learning approach could allow computers to determine the electronic structure of molecules without having to use the most resource-intensive equations of density functional theory, new research suggests (Nat. Commun. 2017, DOI: 10.1038/s41467-017-00839-3).

[+]Enlarge
Credit: Leslie Vogt/New York U
The new machine learning method was able to simulate intramolecular electron transfer in malonaldehyde. The distribution of pink points corresponds to molecular configurations used to train the algorithm. The blue points represent configurations generated independently by the learning algorithm. The turquoise points confirm the predictions in an independent numerical experiment.
Structure of malonaldehyde illustrating computational simulations of intramolecular electron transfer.
Credit: Leslie Vogt/New York U
The new machine learning method was able to simulate intramolecular electron transfer in malonaldehyde. The distribution of pink points corresponds to molecular configurations used to train the algorithm. The blue points represent configurations generated independently by the learning algorithm. The turquoise points confirm the predictions in an independent numerical experiment.

Spam filtering, economic forecasting, and other activities, such as predicting material properties, are powered by algorithms that allow computers to learn from and make predictions on the basis of collections of data. In the case of material properties, computers currently make predictions after being trained with a database of electronic structure information for many types of substances.

A team led by Kieron Burke of the University of California, Irvine; Klaus-Robert Müller of Technical University of Berlin; and Mark E. Tuckerman of New York University now proposes training computers to connect molecules’ structure and properties by having the machines learn from maps of molecular electron density determined from molecules’ potential energy.

After training on existing maps, computers could predict a new molecule’s ground-state electron density. The molecule’s ground-state properties can then be extrapolated from its electron density, as theorized by Pierre Hohenberg and Walter Kohn in the 1960s. In the new work, the team was able to use its “machine learning Hohenberg-Kohn” approach to simulate an intramolecular proton transfer in the enol form of malonaldehyde [CH2(CHO)2].

Article:

This article has been sent to the following recipient:

0 /1 FREE ARTICLES LEFT THIS MONTH Remaining
Chemistry matters. Join us to get the news you need.