Augmentation of Universal Potentials for Broad Applications

Abstract

Universal potentials open the door for DFT level calculations at a fraction of their cost. We find that for application to systems outside the scope of its training data, CHGNet\cite{deng2023chgnet} has the potential to succeed out of the box, but can also fail significantly in predicting the ground state configuration. We demonstrate that via fine-tuning or a $\Delta$-learning approach it is possible to augment the overall performance of universal potentials for specific cluster and surface systems. We utilize this to investigate and explain experimentally observed defects in the Ag(111)-O surface reconstruction and explain the mechanics behind its formation.

References in corpus (25)

• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Less is more: sampling chemical space with active learning
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Optimization of Molecules via Deep Reinforcement Learning
• GPAW: An open Python package for electronic-structure calculations
• Accurate and efficient linear scaling DFT calculations with universal applicability
• $\Delta$-Machine Learning for Potential Energy Surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) Level of Theory
• Gaussian Process Regression for Geometry Optimization
• Experimental and theoretical study of oxygen adsorption structures on Ag(111)
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces
• Updates to the DScribe Library: New Descriptors and Derivatives
• Global optimization of atomistic structure enhanced by machine learning
• Reactive Dynamics and Spectroscopy of Hydrogen Transfer from Neural Network-Based Reactive Potential Energy Surfaces
• Atomistic structure learning
• Atomistic structure search using local surrogate mode
• Generating candidates in global optimization algorithms using complementary energy landscapes
• Top-down formation of ethylene from fragmentation of superhydrogenated polycyclic aromatic hydrocarbons

Cited by in corpus (5)

• $\Delta$-model correction of Foundation Model based on the models own understanding
• Instability of oxide perovskite surfaces induced by vacancy formation
• RAFFLE: Active learning accelerated interface structure prediction
• Active Δ-learning with universal potentials for global structure optimization
• Iterative learning scheme for crystal structure prediction with anharmonic lattice dynamics