Machine Learning Force Fields

Abstract

In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio 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.

Towards modeling spatiotemporal processes in metal–organic frameworks

“…Machine learning potentials While a FF description of the PES increases the spatiotemporal simulation window compared with a QM description, the conversion from a QM PES to a FF PES is typically accompanied by a substantial loss of accuracy and, for nonreactive FFs, does not allow the description of phenomena that are accompanied by bond rearrangements. To overcome these limitations, MLPs can be derived, where a numerical potential is derived from an underlying database of QM data using some (nonlinear) regression procedure [68][69][70][71]. MLPs can be used to calculate much more efficiently the PES with an accuracy matching the underlying QM data.…”

Choosing the right molecular machine learning potential

“…(The force acting on the nuclei is the negative of the PES gradient.) Owing to its generalization capabilities and fast prediction on unseen data, MLPs can be explored to accelerate minimum-energy [10][11][12][13][14][15] and transition-state structure search, 13,16,17 vibrational analysis, 18-21 absorption 22,23 and emission spectra simulation, 24 reaction 13, 25,26 and structural transition exploration, 27 and ground- [3][4][5][6][7][8][9] and excitedstate dynamics propagation. 28,29 A blessing and a curse of ML is that it is possible to design, for all practical purposes, an infinite number of MLP models that can describe a molecular PES.…”

Accelerated Atomistic Modeling of Solid-State Battery Materials With Machine Learning

“…Owing to improving software availability, the adoption of ANN potentials and other MLPs for materials simulations has been gaining momentum in the past few years, as is also evidenced by the rapidly increasing number of publications that mention ANN potentials (Figure 3). Further details of the different MLP methods can be found in perspectives and reviews (Behler, 2016;Mueller et al, 2020;Noé et al, 2020;Behler, 2021;Shao et al, 2021;Unke et al, 2021).…”