Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies

Abstract

We show how to speed up global optimization of molecular structures using machine learning methods. To represent the molecular structures we introduce the auto-bag feature vector that combines: i) a local feature vector for each atom, ii) an unsupervised clustering of such feature vectors for many atoms across several structures, and iii) a count for a given structure of how many times each cluster is represented. During subsequent global optimization searches, accumulated structure-energy relations of relaxed structural candidates are used to assign local energies to each atom using supervised learning. Specifically, the local energies follow from assigning energies to each cluster of local feature vectors and demanding the sum of local energies to amount to the structural energies in the least squares sense. The usefulness of the method is demonstrated in basin hopping searches for 19-atom structures described by single- or double-well Lennard- Jones type potentials and for 24-atom carbon structures described by density functional theory (DFT). In all cases, utilizing the local energy information derived on-the-fly enhances the rate at which the global minimum energy structure is found.

References in corpus (22)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• A real-space grid implementation of the Projector Augmented Wave method
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Ab initio Random Structure Searching
• Molecular geometry optimization with a genetic algorithm
• Machine-learning based interatomic potential for amorphous carbon
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Data-driven learning of total and local energies in elemental boron
• How to quantify energy landscapes of solids
• Adaptive Genetic Algorithm for Crystal Structure Prediction
• Nudged elastic band calculations accelerated with Gaussian process regression
• Designed Interaction Potentials via Inverse Methods for Self-Assembly
• Stability and metastability of clusters in a reactive atmosphere: theoretical evidence for unexpected stoichiometries of MgMOx
• Energy density in density functional theory: Application to crystalline defects and surfaces
• Learning molecular energies using localized graph kernels
• Comment on "Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning"

Cited by in corpus (6)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation
• Mean-Field Density Matrix Decompositions
• Thermometry of one-dimensional Bose gases with neural networks
• A Fuzzy Classification Framework to Identify Equivalent Atoms in Complex Materials and Molecules
• Atomistic Global Optimization X: A Python package for optimization of atomistic structures