Project: Interacting Particle Networks: a new deep learning approach to molecular simulation of condensed phases.
2017-10-01 – 2021-09-30
- Abstract
Force fields are computationally very efficient, yet coarse approximations to the potential energy surface felt by nuclei in molecules. In this project, recent breakthroughs in machine learning will be exploited to increase their reliability. The goal of this work, is to establish force fields with a novel deep learning concept, designed to “understand” many-body interactions: the Interacting Particle Network (IPN).
Show
Sort by
-
Explicit electrons in machine learning potentials
-
Nuclear quantum effects in proton transfer reactions
-
Physical constraints on polarization and charge transport in machine-learning potentials
-
- Journal Article
- A1
- open access
Machine learning potentials for metal-organic frameworks using an incremental learning approach
-
- Journal Article
- A1
- open access
Quantum free energy profiles for molecular proton transfers
-
The influence of nuclear quantum effects on proton hopping kinetics in the H-SSZ-13 zeolite through ab initio derived machine learning potentials
-
Machine learning potentials for metal-organic frameworks with thermodynamic transferability
-
A physically sound basis for polarization in machine-learning force fields
-
Physically sound long-range interactions in machine-learning potentials
-
Supporting data for "Nuclear quantum effects on zeolite proton hopping kinetics explored with machine learning potentials and path integral molecular dynamics"
(2022)