Transfer and Active Learning of High Dimensional Neural Network Potentials for Transition Metal Clusters and Bulk

13 June 2022, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Classical molecular dynamics (MD) simulations represent a very popular and powerful tool for materials modeling and design. The predictive power of MD hinges on the ability of the interatomic potential to capture the underlying physics and chemistry. There have been decades of seminal work on developing interatomic potentials albeit with a focus predominantly on capturing the properties of bulk materials. Such physics-based models, while extensively deployed for predicting dynamics and properties of nanoscale systems over the past two decades, tend to perform poorly in predicting nanoscale potential energy surface when compared to high-fidelity first-principles calculations. These limitations stem from the lack of flexibility in such models, which rely on a pre-defined functional form. Machine learning models and approaches have emerged as a viable alternative to capture the diverse size-dependent cluster geometries, nanoscale dynamics and the complex nanoscale potential energy surfaces (PES), without sacrificing the bulk properties. Here, we introduce an ML workflow that combines transfer and active learning strategies to develop high-dimensional neural networks (NN) for capturing cluster and bulk properties for several different transition metals with applications in catalysis, microelectronics, and energy storage to name a few. Our NN first learns the bulk PES from the high-quality physics-based models in literature and subsequently augments this learning via retraining with a higher fidelity first-principles training dataset to concurrently capture both the nanoscale and bulk PES. Our workflow departs from status-quo in its ability to learn from a sparsely sampled dataset that nonetheless covers a diverse range of cluster configurations from near-equilibrium to highly non-equilibrium as well as learning strategies that iteratively improves the fingerprinting depending on model fidelity. All the developed models are rigorously tested against an extensive first-principles dataset of energies and forces of cluster configurations as well as several properties of bulk configurations for 10 different transition metals. Our approach is material agnostic and provides a methodology to transfer and build upon the learnings from decades of seminal work in molecular simulations on to a new generation of ML trained potentials to accelerate materials discovery and design.


Transfer Learning
Active Learning
Neural Network Potential Model


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.