A causal energetic neural network framework learns thermodynamically consistent history-dependent constitutive laws, proving internal variables are unique up to linear transformation and achieving 2% error on polycrystalline magnesium data.
A learning-based multiscale model for reactive flow in porous media.Water Resources Research, 60(9):e2023WR036303, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Neural-Network Framework to Learn History-Dependent Constitutive Laws and Identifiability of Internal Variables
A causal energetic neural network framework learns thermodynamically consistent history-dependent constitutive laws, proving internal variables are unique up to linear transformation and achieving 2% error on polycrystalline magnesium data.