Hybrid Classical/Machine-Learning Force Fields for the Accurate Description of Molecular Condensed-Phase Systems

Abstract

Electronic structure methods offer in principle accurate predictions of molecular properties, however, their applicability is limited by computational costs. Empirical methods are cheaper, but come with inherent approximations and are dependent on the quality and quantity of training data. The rise of machine learning (ML) force fields (FFs) exacerbates limitations related to training data even further, especially for condensed-phase systems for which the generation of large and high-quality training datasets is difficult. Here, we propose a hybrid ML/classical FF model that is parametrized exclusively on high-quality ab initio data of dimers and monomers in vacuum but is transferable to condensed-phase systems. The proposed hybrid model combines our previous ML-parametrized classical model with ML corrections for situations where classical approximations break down, thus combining the robustness and efficiency of classical FFs with the flexibility of ML. Extensive validation on benchmarking datasets and experimental condensed-phase data, including organic liquids and small-molecule crystal structures, showcases how the proposed approach may promote FF development and unlock the full potential of classical FFs.

References in corpus (19)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• SchNet - a deep learning architecture for molecules and materials
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Machine Learning Unifies the Modelling of Materials and Molecules
• Ab initio theory and modeling of water
• Directional Message Passing for Molecular Graphs
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Computational Complexity of interacting electrons and fundamental limitations of Density Functional Theory
• Minimal Basis Iterative Stockholder: Atoms in Molecules for Force-Field Development
• Reliable and Practical Computational Prediction of Molecular Crystal Polymorphs
• Performance of ab initio and density functional methods for conformational equilibria of CnH2n+2 alkane isomers (n=2-8)
• Interactions between Large Molecules: Puzzle for Reference Quantum-Mechanical Methods
• The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials
• Learning the exchange-correlation functional from nature with fully differentiable density functional theory
• Anharmonic and Quantum Fluctuations in Molecular Crystals: A First-Principles Study of the Stability of Paracetamol
• Computing the Absolute Gibbs Free Energy in Atomistic Simulations: Applications to Defects in Solids
• A complete description of thermodynamic stabilities of molecular crystals
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• DMC-ICE13: ambient and high pressure polymorphs of ice from Diffusion Monte Carlo and Density Functional Theory

Cited by in corpus (2)

• NepoIP/MM: Towards Accurate Biomolecular Simulation with a Machine Learning/Molecular Mechanics Model Incorporating Polarization Effects
• Neural Network Potential with Multi-Resolution Approach Enables Accurate Prediction of Reaction Free Energies in Solution