Machine learning streamlines electronic structure calculations for molecules | October 23, 2017 Issue - Vol. 95 Issue 42 | Chemical & Engineering News
Volume 95 Issue 42 | p. 5 | News of The Week
Issue Date: October 23, 2017

Machine learning streamlines electronic structure calculations for molecules

Approach bypasses the most resource-intensive density functional theory equations
Department: Science & Technology
News Channels: Materials SCENE
Keywords: Computational chemistry, theoretical chemistry, physical chemistry, molecular dynamics, DFT, density functional theory, Kohn-Sham, Hohenberg-Kohn

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
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.
Credit: Leslie Vogt/New York U
Structure of malonaldehyde illustrating computational simulations of intramolecular electron transfer.
 
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.
Credit: Leslie Vogt/New York U

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].

 
Chemical & Engineering News
ISSN 0009-2347
Copyright © American Chemical Society
Comments
Prof Y S Prabhakar (Thu Oct 26 00:20:11 EDT 2017)
The content is neither new nor radical discovery. It qualifies as 'popularization of science and technology' to layman.
Dr. K. Navamani (Sat Oct 28 03:04:39 EDT 2017)
Nowadays high computational sources help to resolve the complicated problems, but people should know about how mechanism happens and their related origin via theory. Then only we can enjoy the beauty of nature/mechanism through perfect understanding.

Leave A Comment

*Required to comment