REVIEW 5 cited by
Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Finding accurate solutions to partial differential equations (PDEs) is a crucial task in all scientific and engineering disciplines. It has recently been shown that machine learning methods can improve the solution accuracy by correcting for effects not captured by the discretized PDE. We target the problem of reducing numerical errors of iterative PDE solvers and compare different learning approaches for finding complex correction functions. We find that previously used learning approaches are significantly outperformed by methods that integrate the solver into the training loop and thereby allow the model to interact with the PDE during training. This provides the model with realistic input distributions that take previous corrections into account, yielding improvements in accuracy with stable rollouts of several hundred recurrent evaluation steps and surpassing even tailored supervised variants. We highlight the performance of the differentiable physics networks for a wide variety of PDEs, from non-linear advection-diffusion systems to three-dimensional Navier-Stokes flows.
Forward citations
Cited by 5 Pith papers
-
TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning
TIDE is a DNS-verified, physically diverse 3D turbulence benchmark with independent ensembles that shows current neural operators barely beat persistence and that low pointwise error does not guarantee physical fidelity.
-
End-to-end differentiable retrieval of molecular spectra using hydrodynamics, chemistry, and radiative transfer
An end-to-end differentiable JAX pipeline couples 1D hydrodynamics, time-dependent chemistry, and radiative transfer, and recovers shock and rate parameters from synthetic HCO+ spectra.
-
No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study
No single flow-surrogate architecture transfers from a boundary-driven Stokes film to a self-sustained Kármán wake; time treatment decides the winner and pointwise RMSE ranks the wrong models.
-
Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields
An attention graph neural network trained only against finite-volume residuals predicts coupled 3D thermo-fluid fields without labeled CFD data, matching or beating a supervised baseline on four benchmarks.
-
Physics-based machine learning for mantle convection simulations
A neural network that predicts divergence-free mantle flow velocities from temperature can replace the Stokes solver in 2D convection simulations, enabling stable rollouts and up to 89x speedup with only 94 training s...
Discussion (0). Continue with ORCID to comment.