Incorporating long-range physics in atomic-scale machine learning.

@article{Grisafi2019IncorporatingLP,
  title={Incorporating long-range physics in atomic-scale machine learning.},
  author={Andrea Grisafi and M. Ceriotti},
  journal={The Journal of chemical physics},
  year={2019},
  volume={151 20},
  pages={
          204105
        }
}
The most successful and popular machine learning models of atomic-scale properties derive their transferability from a locality ansatz. The properties of a large molecule or a bulk material are written as a sum over contributions that depend on the configurations within finite atom-centered environments. The obvious downside of this approach is that it cannot capture nonlocal, nonadditive effects such as those arising due to long-range electrostatics or quantum interference. We propose a… Expand

Figures from this paper

Machine Learning in Computational Surface Science and Catalysis: Case Studies on Water and Metal–Oxide Interfaces
Machine learning-accelerated quantum mechanics-based atomistic simulations for industrial applications
Short solvent model for ion correlations and hydrophobic association
Simulations of water and hydrophobic hydration using a neural network potential
Efficient Long-Range Convolutions for Point Clouds
...
1
2
3
...

References

SHOWING 1-10 OF 83 REFERENCES
Atom-density representations for machine learning.
Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks.
Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis.
...
1
2
3
4
5
...