Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
Computational study of molecules and materials from first principles is a cornerstone of physics, chemistry, and materials science, but limited by the cost of accurate and precise simulations. In settings involving many simulations, machine learning can reduce these costs, often by orders of magnitude, by interpolating between reference simulations. This requires representations that describe any molecule or material and support interpolation. We comprehensively review and discuss current representations and relations between them, using a unified mathematical framework based on many-body functions, group averaging, and tensor products. For selected state-of-the-art representations, we compare energy predictions for organic molecules, binary alloys, and Al-Ga-In sesquioxides in numerical experiments controlled for data distribution, regression method, and hyper-parameter optimization.
Code (6)
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
PET-MAD, a universal interatomic potential for advanced materials modeling
Machine-learning interatomic potentials (MLIPs) have greatly extended the reach of atomic-scale simulations, offering the accuracy of first-principles calculations at a fraction of the effort. Leveraging large quantum me…
DiversityMachine Learning Multiscale Interactions
Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on…
A photonic chip-based machine learning approach for the prediction of molecular properties
Machine learning methods have revolutionized the discovery process of new molecules and materials. However, the intensive training process of neural networks for molecules with ever-increasing complexity has resulted in …
BIG-bench Machine LearningComputational chemistryDrug DiscoveryMolecular Property PredictionAccurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Accurate MD simulations require computationally demanding quantum-mechanical calculations, being practically limited to…
On the propensity of Asn-Gly-containing heptapeptides to form $\beta$-turn structures : comparison between ab initio quantum mechanical calculations and Molecular Dynamics simulations
Both molecular mechanical and quantum mechanical calculations play an important role in describing the behavior and structure of molecules. In this work, we compare for the same peptide systems the results obtained from …