Atomistic Descriptor Optimization Using Complementary Euclidean and Geodesic Distance Information

Abstract

Descriptors are physically-inspired schemes for representing atomistic systems that play a central role in the construction of models of potential energy surfaces. Although physical intuition can be flexibly encoded into descriptor schemes, they are generally ultimately guided only by the spatial or topological arrangement of atoms in the system. Here, we propose a novel approach for the optimization of descriptors based on encoding information about geodesic distances along potential energy manifolds into the hyperparameters of commonly used descriptor schemes. To accomplish this, we combine two ideas: (1) a differential-geometric approach for the fast estimation of approximate geodesic distances; and (2) an information-theoretic evaluation metric - information imbalance - for measuring the shared information between two distance measures. Using the MD22 datasets of ethanol, malonaldehyde, and aspirin, we first show that Euclidean (in Cartesian coordinates) and geodesic distances are inequivalent distance measures, indicating the need for updated ground-truth distance measures that go beyond the Euclidean distance. We then utilize a Bayesian optimization framework to show that descriptors (in this case, atom-centered symmetry functions) can be optimized to maximally express a certain type of distance information, such as Euclidean or geodesic information. We also show that modifying the Bayesian optimization algorithm to minimize a combined Euclidean+geodesic objective function can yield descriptors that not only express both Euclidean and geodesic distance information simultaneously, but in fact resolve substantial disagreements between descriptors optimized to encode only one type of distance measure. We discuss the relevance of our approach to the design of more physically rich and informative descriptors that can encode useful, alternative information about molecular systems.