Adding symmetry-equivariant and conservation-law-constrained layers improves long-horizon accuracy and generalization of neural PDE surrogates on staggered grids.
Enforcing analytic constraints in neural networks emulating physical systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates
Adding symmetry-equivariant and conservation-law-constrained layers improves long-horizon accuracy and generalization of neural PDE surrogates on staggered grids.