Considerations in the use of ML interaction potentials for free energy calculations
arXiv:2403.13952 · doi:10.1063/5.0252043
Abstract
Machine learning force fields (MLFFs) promise to accurately describe the potential energy surface of molecules at the ab initio level of theory with improved computational efficiency. Within MLFFs, equivariant graph neural networks (EQNNs) have shown great promise in accuracy and performance and are the focus of this work. The capability of EQNNs to recover free energy surfaces (FES) remains to be thoroughly investigated. In this work, we investigate the impact of collective variables (CVs) distribution within the training data on the accuracy of EQNNs predicting the FES of butane and alanine dipeptide (ADP). A generalizable workflow is presented in which training configurations are generated with classical molecular dynamics simulations, and energies and forces are obtained with ab initio calculations. We evaluate how bond and angle constraints in the training data influence the accuracy of EQNN force fields in reproducing the FES of the molecules at both classical and ab initio levels of theory. Results indicate that the model's accuracy is unaffected by the distribution of sampled CVs during training, given that the training data includes configurations from characteristic regions of the system's FES. However, when the training data is obtained from classical simulations, the EQNN struggles to extrapolate the free energy for configurations with high free energy. In contrast, models trained with the same configurations on ab initio data show improved extrapolation accuracy. The findings underscore the difficulties in creating a comprehensive training dataset for EQNNs to predict FESs and highlight the importance of prior knowledge of the system's FES.
References in corpus (23)
- Separable Dual Space Gaussian Pseudo-potentials
- Relativistic separable dual-space Gaussian Pseudopotentials from H to Rn
- CP2K: An Electronic Structure and Molecular Dynamics Software Package -- Quickstep: Efficient and Accurate Electronic Structure Calculations
- PLUMED 2: New feathers for an old bird
- On representing chemical environments
- Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
- DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
- E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
- DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
- SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
- sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
- Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
- Exploring the Free Energy Landscape: From Dynamics to Networks and Back
- Machine learning meets quantum physics
- Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
- Deep Learning of Accurate Force Field of Ferroelectric HfO
- MACE-OFF: Transferable Short Range Machine Learning Force Fields for Organic Molecules
- TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials
- Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
- Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
- Micron-scale heterogeneous catalysis with Bayesian force fields from first principles and active learning
- Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size
- On the Atomic Cluster Expansion: interatomic potentials and beyond