First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems.

By J. Behler. Angewandte Chemie, 2017

586 citations recorded by the source corpus.

How researchers see this paper

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

Deep Potentials for Materials Science (2022, background): “BP-NNPs were categorised into four generations [21] for which there are several recent reviews [21–23].”
Machine-learned potentials for next-generation matter simulations (2021, background): “The high-dimensional conformation space combined with potentially high model uncertainties 134 when extrapolating beyond the training space require particular precaution when selecting training data (see the active learning approaches introduced in the previous section).”
Machine learning for heterogeneous catalyst design and discovery (2018, background): “…magnitude higher than ReaxFF and classical interatomic potentials because of the more complex representation of the system that is used in combination with the NN. 76,78 MLPs are being increasingly used to model catalyst dynamics and predict stable surfaces and structures under reaction conditions.”
Machine learning for molecular and materials science (2018, background): “The task of developing transferrable analytic forcefields is a well-defined problem for machine learning.(58,59) It has been demonstrated that, in simple materials, approximate potential energy surfaces learned from quantum mechanical data can save orders of magnitude in processing cost.”