Accelerating Structure Prediction of Molecular Crystals using Actively Trained Moment Tensor Potential

2024/10/04 by Rybin, Nikita, Novikov, Ivan S., Shapeev, Alexander · 4 citations
#FOS: Physical sciences #Materials Science (cond-mat.mtrl-sci) #Soft Condensed Matter (cond-mat.soft)

paper · doi:10.48550/arxiv.2410.03484

Abstract

Inspired by the recent success of machine-learned interatomic potentials for crystal structure prediction of the inorganic crystals, we present a methodology that exploits Moment Tensor Potentials and active learning (based on maxvol algorithm) to accelerate structure prediction of molecular crystals. Benzene and glycine are used as test systems. Interestingly, among obtained low energy structures of benzene we have found a peculiar polymeric benzene structure.

Cited by

• Active learning and explicit electrostatics enable accurate modeling of electrolytes
• Low-rank matrix and tensor approximations: advancing efficiency of machine-learning interatomic potentials
• Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials
• Path-integral molecular dynamics with actively-trained and universal machine learning force fields

Related

• The use of machine learning interatomic potentials for the verification of experimental molecular crystal structures
• FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms
• Predictive crystallography at scale: mapping, validating, and learning from 1000 crystal energy landscapes
• A machine learning potential-based generative algorithm for on-lattice crystal structure prediction
• Fast Prediction of Complex Molecular Crystals by Sensible Selection of Asymmetric Units