AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

Kiwon Um, Robert Brand, Yun (Raymond) Fei, Philipp Holl, Nils Thuerey

NeurIPS 2020 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural PDE solvers · 128 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train corrector with differentiable solver in the loop (SOL32) instead of precomputed corrections (PRE)CNN corrector · Wake FlowMAE velocity: 0.031 -> 0.013Improved
train with solver in the loop (SOL128) instead of non-interacting supervised (NON)CNN corrector · BuoyancyMAE velocity: 1.080 -> 0.620Improved
solver in the loop vs NONCNN corrector · Forced advection-diffusionMAE velocity: 0.159 -> 0.158No clear effect
train CG initial-guess net through differentiable CG solver instead of physics-based residual lossCNN initial guess · CG Solver Poissoniterations to 0.001: 79.03 -> 29.59Improved
solver in the loop vs NONCNN corrector · 3D WakeMAE velocity: 0.144 -> 0.130Improved
increase look-ahead horizon (SOLs -> SOL) (ablation)SOL · Wake FlowMAE velocity: 0.041 -> 0.013Improved
increase look-ahead horizon to 128 steps (ablation)SOL · Buoyancyrelative improvement: up to 40% (1-4 steps) -> 60% (128)Improved
increase look-ahead horizon (ablation)SOL · Adv.-diff.MAE velocity: 0.152 -> 0.158No clear effect
perturb network inputs with Gaussian noise during training (ablation)corrector · Buoyancyrelative improvement: 30.6% -> 34.5%No clear effect
add learned correction to coarse solvercoarse PDE solver · 3D Wakeruntime vs reference: 913.2s -> 13.3sImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy