Atomic Permutationally Invariant Polynomials for Fitting Molecular Force Fields

Abstract

We introduce and explore an approach for constructing force fields for small molecules, which combines intuitive low body order empirical force field terms with the concepts of data driven statistical fits of recent machine learned potentials. We bring these two key ideas together to bridge the gap between established empirical force fields that have a high degree of transferability on the one hand, and the machine learned potentials that are systematically improvable and can converge to very high accuracy, on the other. Our framework extends the atomic Permutationally Invariant Polynomials (aPIP) developed for elemental materials in [Mach. Learn.: Sci. Technol. 2019 1 015004] to molecular systems. The body order decomposition allows us to keep the dimensionality of each term low, while the use of an iterative fitting scheme as well as regularisation procedures improve the extrapolation outside the training set. We investigate aPIP force fields with up to generalised 4-body terms, and examine the performance on a set of small organic molecules. We achieve a high level of accuracy when fitting individual molecules, comparable to those of the many-body machine learned force fields. Fitted to a combined training set of short linear alkanes, the accuracy of the aPIP force field still significantly exceeds what can be expected from classical empirical force fields, while retaining reasonable transferability to both configurations far from the training set and to new molecules.

References in corpus (17)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Less is more: sampling chemical space with active learning
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• De novo exploration and self-guided learning of potential-energy surfaces
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Equation of state of fluid methane from first principles with machine learning potentials
• Comparing the Accuracy of High-Dimensional Neural Network Potentials and the Systematic Molecular Fragmentation Method: A Benchmark Study for all-trans Alkanes
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential

Cited by in corpus (11)

• Perspective on integrating machine learning into computational chemistry and materials science
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
• KLIFF: A framework to develop physics-based and machine learning interatomic potentials
• Mean-Field Density Matrix Decompositions
• No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials
• Probing the effects of broken symmetries in machine learning
• Machine learning based modeling of disordered elemental semiconductors: understanding the atomic structure of a-Si and a-C
• Compressing and forecasting atomic material simulations with descriptors
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems