Machine-learned potentials for next-generation matter simulations

The choice of simulation methods in computational materials science is driven by a fundamental trade-off: bridging large time- and length-scales with highly accurate simulations at an affordable computational cost. Venturing the investigation of complex phenomena on large scales requires fast yet ac...

Full description

Saved in:
Bibliographic Details
Published in:Nature materials 2021-06, Vol.20 (6), p.750-761
Main Authors: Friederich, Pascal, Häse, Florian, Proppe, Jonny, Aspuru-Guzik, Alán
Format: Article
Language:English
Subjects:
639/301/1034
639/301/1034/1035
639/301/1034/1037
639/638/563/981
Biomaterials
Biomolecules
Chemistry and Materials Science
Computational efficiency
Computing costs
Condensed Matter Physics
Crystal structure
Data acquisition
Machine learning
Material properties
Materials Science
Nanotechnology
Optical and Electronic Materials
Organic chemistry
Quantum mechanics
Review Article
Simulation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The choice of simulation methods in computational materials science is driven by a fundamental trade-off: bridging large time- and length-scales with highly accurate simulations at an affordable computational cost. Venturing the investigation of complex phenomena on large scales requires fast yet accurate computational methods. We review the emerging field of machine-learned potentials, which promises to reach the accuracy of quantum mechanical computations at a substantially reduced computational cost. This Review will summarize the basic principles of the underlying machine learning methods, the data acquisition process and active learning procedures. We highlight multiple recent applications of machine-learned potentials in various fields, ranging from organic chemistry and biomolecules to inorganic crystal structure predictions and surface science. We furthermore discuss the developments required to promote a broader use of ML potentials, and the possibility of using them to help solve open questions in materials science and facilitate fully computational materials design. Materials simulations are now ubiquitous for explaining material properties. This Review discusses how machine-learned potentials break the limitations of system-size or accuracy, how active-learning will aid their development, how they are applied, and how they may become a more widely used approach.
ISSN:1476-1122
1476-4660
DOI:10.1038/s41563-020-0777-6