**Atom-centered machine-learning force field package**

L Li and RA Ciufo and JY Lee and C Zhou and B Lin and JY Cho and N Katyal and G Henkelman, COMPUTER PHYSICS COMMUNICATIONS, 292, 108883 (2023).

DOI: 10.1016/j.cpc.2023.108883

In recent years, machine learning algorithms have been widely used for constructing force fields with an accuracy of ab initio methods and the efficiency of classical force fields. Here, we developed a python based atom-centered machine-learning force field (PyAMFF) package to provide a simple and efficient platform for fitting and using machine learning force fields by implementing an atom-centered neural network algorithm with Behler-Parrinello symmetry functions as structural fingerprints. The following three features are included in PyAMFF: (1) integrated Fortran modules for fast fingerprint calculations and Python modules for user-friendly integration through scripts and facile extension of future algorithms; (2) a pure Fortran backend to interface with the software, including the long-timescale dynamic simulation package EON, enabling both molecular dynamic simulations and adaptive kinetic Monte Carlo simulations with machine-learning force fields; and (3) integration with the Atomic Simulation Environment package for active learning and ML- based algorithm development. Here, we demonstrate an efficient parallelization of PyAMFF in terms of CPU and memory usage and show that the Fortran-based PyAMFF calculator exhibits a linear scaling relationship with the number of symmetry functions and the system size.Program summary Program title: python-based atom-centered machine- learning force field (PyAMFF) CPC Library link to program files: https://doi .org /10 .17632 /fsn6dkcvrv.1 Developer's repository link: https://gitlab .com /pyamff /pyamff Licensing provisions: Apache License, 2.0Nature of problem: Determine an approximate (surrogate) model based upon atomic forces and energies from density functional theory (DFT). With a surrogate model that is less computationally expensive to evaluate than DFT, there can be a rapid exploration of the potential energy surface, accelerated optimization to minima and saddle points, and ultimately, accelerated design of active materials where the kinetics are key to the material function. Solution method: The atomic environments of training data are calculated in terms of Behler- Parrinello fingerprints. These fingerprints are passed to a neural network which is trained to reproduce the energy and force of the training data. A parallel implementation and Fortran backend allow for efficient training and calculation of the resulting surrogate model. Examples of long-time simulations of materials on the surrogate model surfaces are provided. (c) 2023 Elsevier B.V. All rights reserved.

Return to Publications page