Perspective: Machine learning potentials for atomistic simulations.

By J. Behler. 2016

1,328 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. K. Müller
2. Frank No'e
3. Alexandre Tkatchenko
4. Alán Aspuru-Guzik
5. Gábor Csányi
6. Klaus‐Robert Müller 
7. A. Pais
8. Tânia F Cova

In Materials Chemistry

1. Alexander V. Shapeev
2. K. Müller
3. Alexandre Tkatchenko
4. Yuri Mishin
5. Evgeny V. Podryabinkin
6. Gábor Csányi
7. Frank No'e
8. Klaus‐Robert Müller 

Citations in the corpus

• The MLIP package: moment tensor potentials with MPI and active learning (2020, background): “Neural network has been the first and are probably the most popular form of regressor for machine-learning potentials [1,4,17,20,60,69,79].”
• Simulations of interfacial processes: recent advances in force field development (2019, background): “Machine learning (ML) has found a valuable place in FF development [56].”
• Machine-Learning Interatomic Potentials for Materials Science (2021, background): “Accordingly, the ML potential are sometimes called “mathematical” or “non-physical” [21].”
• Machine-learned potentials for next-generation matter simulations (2021, background): “…of ML potentials-based MD simulations can be achieved by lowering the dimensionality of the atomic representations of the local chemical environment and overcoming the limitations that arise due to the adverse scaling with the number of elements 40 described by the ML potentials 35,147 .”
• Machine learning for molecular simulation (2019, methodology): “1) [7, 52], but can be trained with force matching if a gradient layer is added to compute the conservative force (Sec.”
• A perspective on conventional high-temperature superconductors at high pressure: Methods and materials (2019, background): “II) Machine learning can also be employed at the level of structural exploration to speed-up the searches by learning inter-atomic model potentials [370, 371].”
• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport (2021, background): “Machine-learning (ML) potentials (or force fields) [1–5], i.e., interatomic potentials constructed based on a ML model, have been demonstrated to be able to achieve an accuracy comparable to their quantum-mechanical training data while reducing the computation time to a small fraction of the…”