MultiPDENet predicts long-term flow dynamics on coarse grids from a few trajectories by embedding finite-difference stencils and Runge-Kutta stepping into a network with macro-scale error correction.
The learning rate is established at 5 × 10−4, with a decay factor of 0.9 applied every 5000 steps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
MultiPDENet predicts long-term flow dynamics on coarse grids from a few trajectories by embedding finite-difference stencils and Runge-Kutta stepping into a network with macro-scale error correction.