A deep learning pipeline classifies five cubic space-group types from EBSD patterns, reaching 98% accuracy on simulated data and 71% to 93% on experimental data depending on which phases are included.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Space Group Determination from EBSD Patterns: The Role of Deep Learning and High-throughput Dynamical Simulations
A deep learning pipeline classifies five cubic space-group types from EBSD patterns, reaching 98% accuracy on simulated data and 71% to 93% on experimental data depending on which phases are included.