npj Computational Materials · 2024 · 16 citations · 71 references
Natural SciencesMaterials EngineeringMaterials ScienceComputational Materials ScienceMachine LearningMaterials CharacterizationAlloysCrystallographyElectron DiffractionElectron MicroscopyMicrostructure AnalysisTransmission Electron MicroscopyClusteringDiffraction PatternsElectron Diffraction Pattern AnalysisHyperparameter OptimizationPhase InformationScanning Transmission Electron MicroscopyStrain MappingTransmission Electron Microscopy Strain Mapping
Four-dimensional scanning transmission electron microscopy, coupled with a wide array of data analytics, has unveiled new insights into complex materials. Here, we introduce a straightforward unsupervised machine learning approach that entails dimensionality reduction and clustering with minimal hyperparameter tuning to semi-automatically identify unique coexisting structures in metallic alloys. Applying cepstral transformation to the original diffraction dataset improves this process by effectively isolating phase information from potential signal ambiguity caused by sample tilt and thickness variations, commonly observed in electron diffraction patterns. In a case study of a NiTiHfAl shape memory alloy, conventional scanning transmission electron microscopy imaging struggles to accurately identify a low-contrast precipitate at lower magnifications, posing challenges for microscale analyses. We find that our method efficiently separates multiple coherent structures while using objective means of determining hyperparameters. Furthermore, we demonstrate how the clustering result facilitates more robust strain mapping to provide immediate and quantitative structural insights.
71
Learning the parts of objects by non-negative matrix factorization
Daniel D. Lee, H. Sebastian Seung · Nature · 1999 · 14.1K citations
Observation of room-temperature polar skyrmions
Sujit Das, Yun‐Long Tang, Zijian Hong et al. · Nature · 2019 · 763 citations · Full text