In modern computational materials,machine learning has shown the capability to predict interatomic potentials,thereby supporting and accelerating conventional molecular dynamics(MD)simulations.However,existing models ...In modern computational materials,machine learning has shown the capability to predict interatomic potentials,thereby supporting and accelerating conventional molecular dynamics(MD)simulations.However,existing models typically sacrifice either accuracy or efficiency.Moreover,efficient models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs.Here,we introduce an efficient equivariant graph neural network(E^(2)GNN)that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals.Rather than relying on higher-order representations,E^(2)GNN employs a scalar-vector dual representation to encode equivariant features.By learning geometric symmetry information,our model remains efficient while ensuring prediction accuracy and robustness through the equivariance.Our results show that E^(2)GNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets,which include catalysts,molecules,and organic isomers.Furthermore,we conductMDsimulations using the E^(2)GNN force field across solid,liquid,and gas systems.It is found that E^(2)GNN can achieve the accuracy of ab initio MD across all examined systems.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.62176272)Research and Development Program of Guangzhou Science and Technology Bureau(No.2023B01J1016)+2 种基金Key-Area Research and Development Program of Guangdong Province(No.2020B1111100001)Singapore MOE Tier 1(No.A-8001194-00-00)Singapore MOE Tier 2(No.A-8001872-00-00).
文摘In modern computational materials,machine learning has shown the capability to predict interatomic potentials,thereby supporting and accelerating conventional molecular dynamics(MD)simulations.However,existing models typically sacrifice either accuracy or efficiency.Moreover,efficient models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs.Here,we introduce an efficient equivariant graph neural network(E^(2)GNN)that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals.Rather than relying on higher-order representations,E^(2)GNN employs a scalar-vector dual representation to encode equivariant features.By learning geometric symmetry information,our model remains efficient while ensuring prediction accuracy and robustness through the equivariance.Our results show that E^(2)GNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets,which include catalysts,molecules,and organic isomers.Furthermore,we conductMDsimulations using the E^(2)GNN force field across solid,liquid,and gas systems.It is found that E^(2)GNN can achieve the accuracy of ab initio MD across all examined systems.
