PyXtal_FF: a python library for automated force field generation

Abstract

We present PyXtal_FF—a package based on Python programming language—for developing machine learning potentials (MLPs). The aim of PyXtal_FF is to promote the application of atomistic simulations through providing several choices of atom-centered descriptors and machine learning regressions in one platform. Based on the given choice of descriptors (including the atom-centered symmetry functions, embedded atom density, SO4 bispectrum, and smooth SO3 power spectrum), PyXtal_FF can train MLPs with either generalized linear regression or neural network models, by simultaneously minimizing the errors of energy/forces/stress tensors in comparison with the data from ab-initio simulations. The trained MLP model from PyXtal_FF is interfaced with the Atomic Simulation Environment (ASE) package, which allows different types of light-weight simulations such as geometry optimization, molecular dynamics simulation, and physical properties prediction. Finally, we will illustrate the performance of PyXtal_FF by applying it to investigate several material systems, including the bulk SiO2, high entropy alloy NbMoTaW, and elemental Pt for general purposes. Full documentation of PyXtal_FF is available at https://pyxtal-ff.readthedocs.io.

Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport

“…Many descriptors have been proposed, including, e.g., Behler's symmetry functions [31], the smooth overlap of atomic positions (SOAP) [30], the bispectrum [7], the Coulomb matrix [32], the moment tensor [17], the atomic cluster expansions [33], the embedded atom descriptor [34], the Gaussian moments [35], and the atomic permutationally invariant polynomials [36]. There are libraries implementing various descriptors [37][38][39].…”

“…( 13) by a weighting factor such as Z j Z k [42], where Z j is the atomic number of atom j, although other weighting factors [43] can also be used. This method has been adopted in the PyXtal_FF package [39] for all the descriptors implemented therein. Based on our definition of g n (r i j ) in Eq.…”

Formation of Linear Oligomers in Solid Electrolyte Interphase via Two‐Electron Reduction of Ethylene Carbonate

“…Various diffusion mechanisms have been proposed based on theory and experiment. [48] One of the advantages of HAIR is the explicit consideration of solvation, especially in such complex reaction conditions as SEI. Nevertheless, the current limitation comes from the limited size that can be accessed in simulation because of the expensive AIMD part.…”

Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport

“…Many descriptors have been proposed, including, e.g., Behler's symmetry functions [28], the smooth overlap of atomic positions (SOAP) [27], the bispectrum [7], the Coulomb matrix [29], the moment tensor [17], the atomic cluster expansions [30], the embedded atom descriptor [31], the Gaussian moments [32], and the atomic permutationally invariant polynomials [33]. There are libraries implementing various descriptors [34][35][36].…”

“…( 13) by a weighting factor such as Z j Z k [39], where Z j is the atomic number of atom j, although other weighting factors [40] can also be used. This method has been adopted in the PyXtal_FF package [36] for all the descriptors implemented therein. Based on our definition of g n (r ij ) in Eq.…”