By mapping PDE residuals and boundary conditions to a fixed latent geometry through deformation gradients, latent PDE mapping improves out-of-distribution geometric generalization in PINNs and PI-DONs for the Aliev-Panfilov cardiac model, with 4–6× lower L2 error on rotation-dominated families.
The openCARP simulation environment for cardiac electrophysiology
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Latent PDE mapping for efficient physics-informed learning across geometries with limited data
By mapping PDE residuals and boundary conditions to a fixed latent geometry through deformation gradients, latent PDE mapping improves out-of-distribution geometric generalization in PINNs and PI-DONs for the Aliev-Panfilov cardiac model, with 4–6× lower L2 error on rotation-dominated families.