Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations.

658 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.

Machine-Learning Interatomic Potentials for Materials Science (2021, methodology): “The reader is referred to Behler’s paper [110] for an excellent exposition of the NN method, including the exact count of the total number of parameters and comparison of different transfer functions.”
Physically informed artificial neural networks for atomistic modeling of materials (2018, methodology): “[15] J.”
Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems (2020, methodology): “…Hansen et al. [120] find that parameterizations of atomic energy using ML take seconds compared to multiple days for more standard quantum-calculation calculations, and Behler et al. [27] find that neural networks can vastly improve the efficiency of finding potential energy surfaces of molecules.”
Machine Learning Force Fields: Construction, Validation, and Outlook (2016, methodology): “Deep learning neural networks 30 and nonlinear regression processes 13 have been the methods of choice for models describing atomic interactions.”