With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties,machine learning methods have tremendously shifted the paradigms of computational sciences underpinning p...With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties,machine learning methods have tremendously shifted the paradigms of computational sciences underpinning physics,material science,chemistry,and biology.While existing machine learning models have yielded superior performances in many occasions,most of them model and process molecular systems in terms of homogeneous graph,which severely limits the expressive power for representing diverse interactions.In practice,graph data with multiple node and edge types is ubiquitous and more appropriate for molecular systems.Thus,we propose the heterogeneous relational message passing network(HermNet),an end-to-end heterogeneous graph neural networks,to efficiently express multiple interactions in a single model with ab initio accuracy.HermNet performs impressively against many top-performing models on both molecular and extended systems.Specifically,HermNet outperforms other tested models in nearly 75%,83%and 69%of tasks on revised Molecular Dynamics 17(rMD17),Quantum Machines 9(QM9)and extended systems datasets,respectively.In addition,molecular dynamics simulations and material property calculations are performed with HermNet to demonstrate its performance.Finally,we elucidate how the design of HermNet is compatible with quantum mechanics from the perspective of the density functional theory.Besides,HermNet is a universal framework,whose sub-networks could be replaced by other advanced models.展开更多
Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has ...Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has a lower computational cost but requires accurate force fields to achieve chemical accuracy.In this work,we develop a symmetry-adapted graph neural network framework called the molecular dynamics graph neural network(MDGNN)to construct force fields automatically for molecular dynamics simulations for both molecules and crystals.This architecture consistently preserves translation,rotation,and permutation invariance in the simulations.We also propose a new feature engineering method that includes high-order terms of interatomic distances and demonstrate that the MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics.In addition,we demonstrate that force fields constructed by the proposed model have good transferability.The MDGNN is thus an efficient and promising option for performing molecular dynamics simulations of large-scale systems with high accuracy.展开更多
The introduction of magnetism in SnTe-class topological crystalline insulators is a challenging subject with great importance in the quantum device applications. Based on the first-principles calculations, we have stu...The introduction of magnetism in SnTe-class topological crystalline insulators is a challenging subject with great importance in the quantum device applications. Based on the first-principles calculations, we have studied the defect energetics and magnetic properties of 3d transition-metal(TM)-doped SnTe. We find that the doped TM atoms prefer to stay in the neutral states and have comparatively high formation energies, suggesting that the uniform TMdoping in SnTe with a higher concentration will be difficult unless clustering. In the dilute doping regime, all the magnetic TMatoms are in the high-spin states, indicating that the spin splitting energy of 3d TM is stronger than the crystal splitting energy of the SnTe ligand. Importantly, Mn-doped SnTe has relatively low defect formation energy, largest local magnetic moment, and no defect levels in the bulk gap, suggesting that Mn is a promising magnetic dopant to realize the magnetic order for the theoretically-proposed large-Chern-number quantum anomalous Hall effect(QAHE) in SnTe.展开更多
基金This work was supported by the Basic Science Center Project of NSFC(Grant No.51788104)the Ministry of Science and Technology of China(Grants Nos.2018YFA0307100,and 2018YFA0305603)+3 种基金the National Science Fund for Distinguished Young Scholars(Grant No.12025405)the National Natural Science Foundation of China(Grant No.11874035)Tsinghua University Initiative Scientific Research Programthe Beijing Advanced Innovation Center for Future Chip(ICFC).
文摘With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties,machine learning methods have tremendously shifted the paradigms of computational sciences underpinning physics,material science,chemistry,and biology.While existing machine learning models have yielded superior performances in many occasions,most of them model and process molecular systems in terms of homogeneous graph,which severely limits the expressive power for representing diverse interactions.In practice,graph data with multiple node and edge types is ubiquitous and more appropriate for molecular systems.Thus,we propose the heterogeneous relational message passing network(HermNet),an end-to-end heterogeneous graph neural networks,to efficiently express multiple interactions in a single model with ab initio accuracy.HermNet performs impressively against many top-performing models on both molecular and extended systems.Specifically,HermNet outperforms other tested models in nearly 75%,83%and 69%of tasks on revised Molecular Dynamics 17(rMD17),Quantum Machines 9(QM9)and extended systems datasets,respectively.In addition,molecular dynamics simulations and material property calculations are performed with HermNet to demonstrate its performance.Finally,we elucidate how the design of HermNet is compatible with quantum mechanics from the perspective of the density functional theory.Besides,HermNet is a universal framework,whose sub-networks could be replaced by other advanced models.
基金This work was supported by the Basic Science Center Project of National Natural Science Foundation of China(Grant No.51788104)the Ministry of Science and Technology of China(Grant Nos.2016YFA0301001,and 2017YFB0701502)the Beijing Advanced Innovation Center for Materials Genome Engineering.
文摘Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has a lower computational cost but requires accurate force fields to achieve chemical accuracy.In this work,we develop a symmetry-adapted graph neural network framework called the molecular dynamics graph neural network(MDGNN)to construct force fields automatically for molecular dynamics simulations for both molecules and crystals.This architecture consistently preserves translation,rotation,and permutation invariance in the simulations.We also propose a new feature engineering method that includes high-order terms of interatomic distances and demonstrate that the MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics.In addition,we demonstrate that force fields constructed by the proposed model have good transferability.The MDGNN is thus an efficient and promising option for performing molecular dynamics simulations of large-scale systems with high accuracy.
基金supported by the National Key Research and Development Program,the National Natural Science Foundation of China(Grant Nos.11334006 and 11504015)the Open Research Fund Program of the State Key Laboratory of Low-dimensional Quantum Physics(Grant No.KF201508)
文摘The introduction of magnetism in SnTe-class topological crystalline insulators is a challenging subject with great importance in the quantum device applications. Based on the first-principles calculations, we have studied the defect energetics and magnetic properties of 3d transition-metal(TM)-doped SnTe. We find that the doped TM atoms prefer to stay in the neutral states and have comparatively high formation energies, suggesting that the uniform TMdoping in SnTe with a higher concentration will be difficult unless clustering. In the dilute doping regime, all the magnetic TMatoms are in the high-spin states, indicating that the spin splitting energy of 3d TM is stronger than the crystal splitting energy of the SnTe ligand. Importantly, Mn-doped SnTe has relatively low defect formation energy, largest local magnetic moment, and no defect levels in the bulk gap, suggesting that Mn is a promising magnetic dopant to realize the magnetic order for the theoretically-proposed large-Chern-number quantum anomalous Hall effect(QAHE) in SnTe.
