A sine-activated PINN with elastic-equilibrium and compatibility priors reconstructs 4D-STEM strain maps from 10% of probe positions on one experimental dataset (R2(εxx) = 0.80), with explicit caveats about single-mask evaluation and a mild information leak.
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
-
Physics-Informed Neural Networks for Sparse Strain-Field Reconstruction in 4D-STEM
A sine-activated PINN with elastic-equilibrium and compatibility priors reconstructs 4D-STEM strain maps from 10% of probe positions on one experimental dataset (R2(εxx) = 0.80), with explicit caveats about single-mask evaluation and a mild information leak.