Application-specific machine-learned interatomic potentials: exploring the trade-off between DFT convergence, MLIP expressivity, and computational cost

Abstract

Machine-learned interatomic potentials (MLIPs) are revolutionizing computational materials science and chemistry by offering an efficient alternative to {\em ab initio} molecular dynamics (MD) simulations. However, fitting high-quality MLIPs remains a challenging, time-consuming, and computationally intensive task where numerous trade-offs have to be considered, e.g., How much and what kind of atomic configurations should be included in the training set? Which level of {\em ab initio} convergence should be used to generate the training set? Which loss function should be used for fitting the MLIP? Which machine learning architecture should be used to train the MLIP? The answers to these questions significantly impact both the computational cost of MLIP training and the accuracy and computational cost of subsequent MLIP MD simulations. In this study, we use a configurationally diverse beryllium dataset and quadratic spectral neighbor analysis potential. We demonstrate that joint optimization of energy versus force weights, training set selection strategies, and convergence settings of the {\em ab initio} reference simulations, as well as model complexity can lead to a significant reduction in the overall computational cost associated with training and evaluating MLIPs. This opens the door to computationally efficient generation of high-quality MLIPs for a range of applications which demand different accuracy versus training and evaluation cost trade-offs.

References in corpus (22)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Active learning of linearly parametrized interatomic potentials
• Machine learning a general purpose interatomic potential for silicon
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces
• Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
• EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
• Ultra-fast interpretable machine-learning potentials
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Automated optimization of convergence parameters in plane wave density functional theory calculations via a tensor decomposition-based uncertainty quantification
• $\Delta$-model correction of Foundation Model based on the models own understanding
• Universal Machine Learning Interatomic Potentials are Ready for Phonons
• Multi-fidelity learning for interatomic potentials: Low-level forces and high-level energies are all you need
• Fine-tuning foundation models of materials interatomic potentials with frozen transfer learning
• Information-entropy-driven generation of material-agnostic datasets for machine-learning interatomic potentials