Predicting nanomaterial(NM)fate requires more than structural snapshots and degradation curves.Current 2D models,which focus on space(structural change)and time(kinetics),provide valuable insights but remain incomplet...Predicting nanomaterial(NM)fate requires more than structural snapshots and degradation curves.Current 2D models,which focus on space(structural change)and time(kinetics),provide valuable insights but remain incomplete.They cannot fully explain why identical NM behave differently across environments.Here,this Comment proposes a 3D framework that adds a critical third axis—environmental hierarchy—to capture transformations that are orthogonal to space and time.展开更多
Graph deep learning models,which incorporate a natural inductive bias for atomic structures,are of immense interest in materials science and chemistry.Here,we introduce the Materials Graph Library(MatGL),an open-sourc...Graph deep learning models,which incorporate a natural inductive bias for atomic structures,are of immense interest in materials science and chemistry.Here,we introduce the Materials Graph Library(MatGL),an open-source graph deep learning library for materials science and chemistry.Built on top of the popular Deep Graph Library(DGL)and Python Materials Genomics(Pymatgen)packages,MatGL is designed to be an extensible“batteries-included”library for developing advanced model architectures for materials property predictions and interatomic potentials.At present,MatGL has efficient implementations for both invariant and equivariant graph deep learning models,including the Materials 3-body Graph Network(M3GNet),MatErials Graph Network(MEGNet),Crystal Hamiltonian Graph Network(CHGNet),TensorNet and SO3Net architectures.MatGL also provides several pretrained foundation potentials(FPs)with coverage of the entire periodic table,and property prediction models for out-of-box usage,benchmarking and fine-tuning.Finally,MatGL integrates with PyTorch Lightning to enable efficient model training.展开更多
基金SC acknowledges UK Research and Innovation-Natural Environment Research Council Independent Research Fellowship(NE/B000187/1)for supporting this work.
文摘Predicting nanomaterial(NM)fate requires more than structural snapshots and degradation curves.Current 2D models,which focus on space(structural change)and time(kinetics),provide valuable insights but remain incomplete.They cannot fully explain why identical NM behave differently across environments.Here,this Comment proposes a 3D framework that adds a critical third axis—environmental hierarchy—to capture transformations that are orthogonal to space and time.
基金intellectually led by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Materials Sciences and Engineering Division under contract No. DE-AC02-05-CH11231 (Materials Project program KC23MP). This research used resources of the National Energy Research Scientific Computing Center (NERSC), a Department of Energy Office of Science User Facility using NERSC award DOE-ERCAP0026371. T.W.Ko also acknowledges the support of the Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship, a Schmidt Futures program. We also acknowledged AdvanceSoft Corporation for implementing the LAMMPS interface.
文摘Graph deep learning models,which incorporate a natural inductive bias for atomic structures,are of immense interest in materials science and chemistry.Here,we introduce the Materials Graph Library(MatGL),an open-source graph deep learning library for materials science and chemistry.Built on top of the popular Deep Graph Library(DGL)and Python Materials Genomics(Pymatgen)packages,MatGL is designed to be an extensible“batteries-included”library for developing advanced model architectures for materials property predictions and interatomic potentials.At present,MatGL has efficient implementations for both invariant and equivariant graph deep learning models,including the Materials 3-body Graph Network(M3GNet),MatErials Graph Network(MEGNet),Crystal Hamiltonian Graph Network(CHGNet),TensorNet and SO3Net architectures.MatGL also provides several pretrained foundation potentials(FPs)with coverage of the entire periodic table,and property prediction models for out-of-box usage,benchmarking and fine-tuning.Finally,MatGL integrates with PyTorch Lightning to enable efficient model training.
