Neural Network Potentials: A Concise Overview of Methods

Abstract

In the past two decades, machine learning potentials (MLP) have reached a level of maturity that now enables applications to large-scale atomistic simulations of a wide range of systems in chemistry, physics and materials science. Different machine learning algorithms have been used with great success in the construction of these MLPs. In this review, we discuss an important group of MLPs relying on artificial neural networks to establish a mapping from the atomic structure to the potential energy. In spite of this common feature, there are important conceptual differences, which concern the dimensionality of the systems, the inclusion of longrange electrostatic interactions, global phenomena like non-local charge transfer, and the type of descriptor used to represent the atomic structure, which can either be predefined or learnable. A concise overview is given along with a discussion of the open challenges in the field.

Towards On-Chip Learning for Low Latency Reasoning with End-to-End Synthesis

“…(3) Neural Networks Potentials (NNPs). NNPs are a way to represent the multidimensional potential energy surface (PES) leveraging machine learning [10]. The PES is of central importance for reaching an atomic-level understanding of any type of system, and contains all the information about the stable and metastable structures, the atomic forces driving the dynamics at finite temperatures, the transition states and barriers governing reactions and structural transitions, and also the atomic vibrations.…”