The Rise of Neural Networks for Materials and Chemical Dynamics

Maksim Kulichenko, Justin S. Smith, Benjamin Nebgen, Ying Wai Li, Nikita Fedik, Alexander I. Boldyrev, Nicholas Lubbers, Kipton Barros, Sergei Tretiak

Research output: Contribution to journalReview articlepeer-review

7 Citations (Scopus)


Machine learning (ML) is quickly becoming a premier tool for modeling chemical processes and materials. ML-based force fields, trained on large data sets of high-quality electron structure calculations, are particularly attractive due their unique combination of computational efficiency and physical accuracy. This Perspective summarizes some recent advances in the development of neural network-based interatomic potentials. Designing high-quality training data sets is crucial to overall model accuracy. One strategy is active learning, in which new data are automatically collected for atomic configurations that produce large ML uncertainties. Another strategy is to use the highest levels of quantum theory possible. Transfer learning allows training to a data set of mixed fidelity. A model initially trained to a large data set of density functional theory calculations can be significantly improved by retraining to a relatively small data set of expensive coupled cluster theory calculations. These advances are exemplified by applications to molecules and materials.

Original languageEnglish
Pages (from-to)6227-6243
Number of pages17
JournalJournal of Physical Chemistry Letters
Issue number26
Publication statusPublished - 8 Jul 2021
Externally publishedYes


Dive into the research topics of 'The Rise of Neural Networks for Materials and Chemical Dynamics'. Together they form a unique fingerprint.

Cite this