Most AI-for-Materials research to date has focused on ideal crystals,whereas real-world materials inevitably contain defects that play a critical role in modern functional technologies.The defects break geometric symm...Most AI-for-Materials research to date has focused on ideal crystals,whereas real-world materials inevitably contain defects that play a critical role in modern functional technologies.The defects break geometric symmetry and increase interaction complexity,posing particular challenges for traditional ML models.Here,we introduce Defect-Informed Equivariant Graph Neural Network(DefiNet),a model specifically designed to accurately capture defect-related interactions and geometric configurations in point-defect structures.DefiNet achieves near-DFT-level structural predictions in milliseconds using a single GPU.To validate its accuracy,we perform DFT relaxations using DefiNet-predicted structures as initial configurations and measure the residual ionic steps.For most defect structures,regardless of defect complexity or system size,only 3 ionic steps are required to reach the DFT-level ground state.Finally,comparisons with scanning transmission electron microscopy(STEM)images confirm DefiNet’s scalability and extrapolation beyond point defects,positioning it as a valuable tool for defect-focused materials research.展开更多
基金supported by the Natural Science Foundation of Guangdong Province (Grant No. 2025A1515011487)Ministry of Education, Singapore, Tier 1 (Grant No. A-8001194-00-00)+1 种基金Tier 2 (Grant No. A-8001872-00-00)lunder its Research Center of Excellence award to the Institute for Functional Intelligent Materials (I-FIM, project No. EDUNC-33-18-279-V12)K.S.N. is grateful to the Royal Society (UK, grant number RSRP\R\190000) for support.
文摘Most AI-for-Materials research to date has focused on ideal crystals,whereas real-world materials inevitably contain defects that play a critical role in modern functional technologies.The defects break geometric symmetry and increase interaction complexity,posing particular challenges for traditional ML models.Here,we introduce Defect-Informed Equivariant Graph Neural Network(DefiNet),a model specifically designed to accurately capture defect-related interactions and geometric configurations in point-defect structures.DefiNet achieves near-DFT-level structural predictions in milliseconds using a single GPU.To validate its accuracy,we perform DFT relaxations using DefiNet-predicted structures as initial configurations and measure the residual ionic steps.For most defect structures,regardless of defect complexity or system size,only 3 ionic steps are required to reach the DFT-level ground state.Finally,comparisons with scanning transmission electron microscopy(STEM)images confirm DefiNet’s scalability and extrapolation beyond point defects,positioning it as a valuable tool for defect-focused materials research.
