Nonadiabatic Dynamics in Two-Dimensional Perovskites Assisted by Machine Learned Force Fields

Abstract

An exploration of the "on-the-fly" nonadiabatic couplings (NACs) for nonradiative relaxation and recombination of excited states in 2D Dion− Jacobson (DJ) lead halide perovskites (LHPs) is accelerated by a machine learning approach. Specifically, ab initio molecular dynamics (AIMD) of nanostructures composed of heavy elements is performed with the use of machine-learning forcefields (MLFFs), as implemented in the Vienna Ab initio Simulation Package (VASP). The force field parametrization is established using on-the-fly learning, which continuously builds a force field using AIMD data. At each time step of the molecular dynamics (MD) simulation, the total energy and forces are predicted based on the MLFF and if the Bayesian error estimate exceeds a threshold, an ab initio calculation is performed, which is used to construct a new force field. Model training of MLFF and evaluation were performed for a range of DJ-LHP models of different thicknesses and halide compositions. The MLFF-MD trajectories were evaluated against pure AIMD trajectories to assess the level of discrepancy and error accumulation. To examine the practical effectiveness of this approach, we have used the MLFF-based MD trajectories to compute NAC and excited-state dynamics. At each stage, results based on machine learning are compared to traditional ab initio based electronic dissipative dynamics. We find that MLFF-MD provides comparable results to AIMDs when MLFF is trained in an NPT ensemble.

Virtual Special Issue on Machine Learning in Physical Chemistry Volume 2

“…In JPC C , the special issue papers describe ML and other data science techniques utilized in the scope of nanoparticles and nanostructures; surface and interface processes; electron, ion, and thermal transport; optic, electronic, and optoelectronic materials; and catalysts and catalysis; as well as energy conversion and storage materials and processes. As in the Parts A and B, a number of articles directly address either the development of new methods or the use of ML methods in new ways. − Several contributions relate to methods in the use or development of so-called machine learning potentials (MLP) or machine learning interaction potentials (MLIP), including a Perspective on improving these models authored by Maxson et al, as well as other contributions. − Interfaces and related phenomena are addressed in several articles. − Nanomaterials and their properties are also prominently featured. − Another large category in JPC C includes studies that address the calculation of properties of materials for wide-ranging applications. − …”