An Atomistic Fingerprint Algorithm for Learning Ab Initio Molecular Force Fields

Abstract

Molecular fingerprints, i.e. feature vectors describing atomistic neighborhood configurations, is an important abstraction and a key ingredient for data-driven modeling of potential energy surface and interatomic force. In this paper, we present the Density-Encoded Canonically Aligned Fingerprint (DECAF) fingerprint algorithm, which is robust and efficient, for fitting per-atom scalar and vector quantities. The fingerprint is essentially a continuous density field formed through the superimposition of smoothing kernels centered on the atoms. Rotational invariance of the fingerprint is achieved by aligning, for each fingerprint instance, the neighboring atoms onto a local canonical coordinate frame computed from a kernel minisum optimization procedure. We show that this approach is superior over PCA-based methods especially when the atomistic neighborhood is sparse and/or contains symmetry. We propose that the `distance' between the density fields be measured using a volume integral of their pointwise difference. This can be efficiently computed using optimal quadrature rules, which only require discrete sampling at a small number of grid points. We also experiment on the choice of weight functions for constructing the density fields, and characterize their performance for fitting interatomic potentials. The applicability of the fingerprint is demonstrated through a set of benchmark problems.

Cited by in corpus (12)

• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Measuring surface charge: why experimental characterization and molecular modeling should be coupled
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Prediction of Atomization Energy Using Graph Kernel and Active Learning
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• A Learned Generalized Geodesic Distance Function-Based Approach for Node Feature Augmentation on Graphs