Training Data Selection for Accuracy and Transferability of Interatomic Potentials
Preprint
Abstract
Advances in machine learning (ML) techniques have enabled the development of interatomic potentials that promise both the accuracy of first principles methods and the low-cost, linear scaling, and parallel efficiency of empirical potentials. Despite rapid progress in the last few years, ML-based potentials often struggle to achieve transferability, that is, to provide consistent accuracy across configurations that significantly differ from those used to train the model. In order to truly realize the promise of ML-based interatomic potentials, it is therefore imperative to develop systematic and scalable approaches for the generation of diverse training sets that ensure broad coverage of the space of atomic environments. This work explores a diverse-by-construction approach that leverages the optimization of the entropy of atomic descriptors to create a very large ($>2\cdot10^{5}$ configurations, $>7\cdot10^{6}$ atomic environments) training set for tungsten in an automated manner, i.e., without any human intervention. This dataset is used to train polynomial as well as multiple neural network potentials with different architectures. For comparison, a corresponding family of potentials were also trained on an expert-curated dataset for tungsten. The models trained to entropy-optimized data exhibited vastly superior transferability compared to the expert-curated models. Furthermore, while the models trained with heavy user input (i.e., domain expertise) yield the lowest errors when tested on similar configurations, out-sample predictions are dramatically more robust when the models are trained on a deliberately diverse set of training data. Herein we demonstrate the development of both accurate and transferable ML potentials using automated and data-driven approaches for generating large and diverse training sets.
Keywords
All Related Versions
This publication has 51 references indexed in Scilit:
- LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scalesComputer Physics Communications, 2022
- A physics-informed operator regression framework for extracting data-driven continuum modelsComputer Methods in Applied Mechanics and Engineering, 2021
- Analysis on block chain financial transaction under artificial neural network of deep learningJournal of Computational and Applied Mathematics, 2020
- Machine learning guided association of adverse drug reactions with in vitro target-based pharmacologyEBioMedicine, 2020
- Data-driven modeling and learning in science and engineeringComptes Rendus Mécanique, 2019
- Materials informaticsJournal of Intelligent Manufacturing, 2018
- Active learning of linearly parametrized interatomic potentialsComputational Materials Science, 2017
- Considerations for choosing and using force fields and interatomic potentials in materials science and engineeringCurrent Opinion in Solid State and Materials Science, 2013
- Key computational modeling issues in Integrated Computational Materials EngineeringComputer-Aided Design, 2013
- Principal Component Analysis2005