Cargando…

NewtonNet: a Newtonian message passing network for deep learning of interatomic potentials and forces

We report a new deep learning message passing network that takes inspiration from Newton's equations of motion to learn interatomic potentials and forces. With the advantage of directional information from trainable force vectors, and physics-infused operators that are inspired by Newtonian phy...

Descripción completa

Detalles Bibliográficos
Autores principales: Haghighatlari, Mojtaba, Li, Jie, Guan, Xingyi, Zhang, Oufan, Das, Akshaya, Stein, Christopher J., Heidar-Zadeh, Farnaz, Liu, Meili, Head-Gordon, Martin, Bertels, Luke, Hao, Hongxia, Leven, Itai, Head-Gordon, Teresa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: RSC 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9189860/
https://www.ncbi.nlm.nih.gov/pubmed/35769203
http://dx.doi.org/10.1039/d2dd00008c
Descripción
Sumario:We report a new deep learning message passing network that takes inspiration from Newton's equations of motion to learn interatomic potentials and forces. With the advantage of directional information from trainable force vectors, and physics-infused operators that are inspired by Newtonian physics, the entire model remains rotationally equivariant, and many-body interactions are inferred by more interpretable physical features. We test NewtonNet on the prediction of several reactive and non-reactive high quality ab initio data sets including single small molecules, a large set of chemically diverse molecules, and methane and hydrogen combustion reactions, achieving state-of-the-art test performance on energies and forces with far greater data and computational efficiency than other deep learning models.