Trained on one AlCrFeNi composition and a single precipitate, an autoencoder-graph-LSTM predicts long-horizon BCC/FCC evolution and reports zero-shot transfer to larger domains, more precipitates, and nearby compositions.
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
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Learning for Accelerated Long-Horizon Forecasting of Multicomponent Multiphase Microstructure Evolution in High-Entropy Alloys
Trained on one AlCrFeNi composition and a single precipitate, an autoencoder-graph-LSTM predicts long-horizon BCC/FCC evolution and reports zero-shot transfer to larger domains, more precipitates, and nearby compositions.