Generating Minimal Training Sets for Machine Learned Potentials
- 15 April 2024
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 132 (16) , 167301
Abstract
This Letter presents a novel approach for identifying uncorrelated atomic configurations from extensive datasets with a nonstandard neural network workflow known as random network distillation (RND) for training machine-learned interatomic potentials (MLPs). This method is coupled with a DFT workflow wherein initial data are generated with cheaper classical methods before only the minimal subset is passed to a more computationally expensive ab initio calculation. This benefits training not only by reducing the number of expensive DFT calculations required but also by providing a pathway to the use of more accurate quantum mechanical calculations. The method’s efficacy is demonstrated by constructing machine-learned interatomic potentials for the molten salts KCl and NaCl. Our RND method allows accurate models to be fit on minimal datasets, as small as 32 configurations, reducing the required structures by at least 1 order of magnitude compared to alternative methods. This reduction in dataset sizes not only substantially reduces computational overhead for training data generation but also provides a more comprehensive starting point for active-learning procedures.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (EXC 2075-390740016, 497249646)
This publication has 38 references indexed in Scilit:
- Efficient Training of Machine Learning Potentials by a Randomized Atomic-System GeneratorThe Journal of Physical Chemistry B, 2020
- Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning PotentialsJournal of Chemical Theory and Computation, 2020
- DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamicsComputer Physics Communications, 2018
- Molecular simulations of the thermal and transport properties of alkali chloride salts for high-temperature thermal energy storageInternational Journal of Heat and Mass Transfer, 2016
- Fast Parallel Algorithms for Short-Range Molecular DynamicsJournal of Computational Physics, 1995
- Ionic sizes and born repulsive parameters in the NaCl-type alkali halides—IIJournal of Physics and Chemistry of Solids, 1964
- Ionic sizes and born repulsive parameters in the NaCl-type alkali halides—IJournal of Physics and Chemistry of Solids, 1964
- The density of liquid NaCl and KCl and an estimate of their critical constants together with those of the other alkali halidesJournal of Inorganic and Nuclear Chemistry, 1962
- Short-range correlations in nuclear wave functionsNuclear Physics, 1960
- Zur Gittertheorie der IonenkristalleThe European Physical Journal A, 1932