Generalizability of Graph Neural Network Force Fields for Predicting Solid-State Properties
This addresses the need for reliable MLFFs in studying complex solid-state materials, though it is incremental as it focuses on benchmarking and data engineering strategies.
This work tackled the problem of ensuring generalizability in machine-learned force fields (MLFFs) for solid materials by testing a graph neural network (GNN)-based MLFF trained on Lennard-Jones Argon on unseen solid-state phenomena, such as phonon density of states and vacancy migration, and found it captured these properties with good agreement to reference data.
Machine-learned force fields (MLFFs) promise to offer a computationally efficient alternative to ab initio simulations for complex molecular systems. However, ensuring their generalizability beyond training data is crucial for their wide application in studying solid materials. This work investigates the ability of a graph neural network (GNN)-based MLFF, trained on Lennard-Jones Argon, to describe solid-state phenomena not explicitly included during training. We assess the MLFF's performance in predicting phonon density of states (PDOS) for a perfect face-centered cubic (FCC) crystal structure at both zero and finite temperatures. Additionally, we evaluate vacancy migration rates and energy barriers in an imperfect crystal using direct molecular dynamics (MD) simulations and the string method. Notably, vacancy configurations were absent from the training data. Our results demonstrate the MLFF's capability to capture essential solid-state properties with good agreement to reference data, even for unseen configurations. We further discuss data engineering strategies to enhance the generalizability of MLFFs. The proposed set of benchmark tests and workflow for evaluating MLFF performance in describing perfect and imperfect crystals pave the way for reliable application of MLFFs in studying complex solid-state materials.