Oliver T. Unke

Machine Learning Force Fields / Oliver T. Unke; Stefan Chmiela; Huziel E. Sauceda [and others]. - 1 online resource (1 article).

Publication type: Review article. Linked open-access copy: published version.

Open access; no subscription required for the linked open-access version.

methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.


Creative Commons Attribution-NonCommercial-NoDerivatives (licence family recorded by the source; version not supplied in metadata).


In English.

10.1021/acs.chemrev.0c01111 doi


machine learning interatomic potentials
potential energy surface
chemical bonding
interatomic interactions
molecular dynamics simulation

B. Sc. Artificial Intelligence UMUN open access collection machine learning


Review articles.