![]() However, a critical limitation of empirical IAPs is that they are approximate models of true physics/chemistry and as such have to be fitted to reproduce reference data from experimental or quantum calculations. Given a local (i.e., short-ranged) IAP, MD simulations can leverage large parallel computers since the calculation of forces can efficiently be decomposed into independent computations that can be concurrently executed 16, thus enabling extremely large simulations 17, 18 that would be impossible with direct quantum simulations. An accurate IAP is critical because large-scale MD simulations using traditional quantum ab initio calculations such as Density Functional Theory (DFT) are prohibitively expensive beyond a few hundred atoms. A key component is the interatomic potential (IAP) 11, 12, 13, 14, 15, i.e., the model form that maps local atomic environments to energies and forces needed to carry out a finite time integration step. However, performing accurate and robust large-scale MD simulations is not a trivial task because this requires the integration of multiple components, as Fig. In this manuscript, we focus on application to classical molecular dynamics (MD), which is a powerful technique for exploring and understanding the behavior of materials at the atomic scale. For that reason, it is often extremely difficult to predict “real-world” performance where unfamiliar inputs are likely to be encountered. Moreover, the accuracy of a machine-learned model can only be quantified using the training itself, or on a subset thereof, held out as validation. While many of these models have proved extremely powerful, new questions and challenges have arisen due to the uncertainty in model predictions coined as extrapolations 10, i.e., when prediction occurs on input that are found outside of the support of the training data. The diversity of applications arising from this swell of attention has brought about data-driven models that have accelerated pharmaceutical design 1, 2, 3, material design 4, 5, the processing of observations of celestial objects 6, and enabled accurate surrogate models of traditional physical simulations 7, 8, 9. The rapid adoption of machine learning (ML) methods in virtually all domains of physical science has caused a disruptive shift in the expectations of accuracy versus computational expense of data-driven models. Furthermore, the models trained to the expert-curated set exhibited a significant decrease in performance when evaluated on out-of-sample configurations. ![]() The models trained to the entropy-optimized data exhibited superior transferability compared to the expert-curated models. A corresponding set of potentials are trained on an expert-curated dataset for tungsten for comparison. Subsequently, multiple polynomial and neural network potentials are trained on the entropy-optimized dataset. This work creates a diverse training set for tungsten in an automated manner using an entropy optimization approach. In order to realize the promise of ML-based potentials, systematic and scalable approaches to generate diverse training sets need to be developed. However, ML-based potentials struggle to achieve transferability, i.e., provide consistent accuracy across configurations that differ from those used during training. ![]() Advances in machine learning (ML) have enabled the development of interatomic potentials that promise the accuracy of first principles methods and the low-cost, parallel efficiency of empirical potentials.
0 Comments
Leave a Reply. |