AI Paper Atlas

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

A composable machine-learning approach for steady-state simulations on high-resolution grids

Rishikesh Ranade, Derek Christopher Hill, Lalit Ghule, Jay Pathak

NeurIPS 2022 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed operator learning · 3 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
subdomain resolution 32^2 to 64^2 (ablation)CoMLSim · 2-D linear Poissonmean absolute error: 0.015 -> 0.011Improved
subdomain resolution 64^2 to 128^2 (ablation)CoMLSim · 2-D linear Poissonmean absolute error: 0.011 -> 0.029Hurt
subdomain resolution 64^2 to 128^2 (ablation)CoMLSim · 2-D linear Poissoniterations to convergence: 162 -> 89Improved
use Gauss Seidel instead of Point Jacobi (ablation)CoMLSim · 2-D linear Poissontime to converge (seconds): 4.3 -> 72Hurt
use Gauss Seidel instead of Point Jacobi (ablation)CoMLSim · 2-D linear Poissonmean absolute error: 0.013 -> 0.017No clear effect
replace multiple subdomains by a single subdomain (no local learning) (ablation)CoMLSim · 2-D linear Poissonmean absolute error: 0.011 -> 0.072Hurt
CoMLSim instead of FNO (best baseline)2-D linear Poisson · 2-D linear PoissonL1 error: 0.031 -> 0.011Improved
CoMLSim instead of UNet on chip cooling3-D chip cooling · 3-D chip coolingL-infinity error: 95.21 -> 15.2Improved
initialize with coarse-grid solution instead of zero or noise (ablation)CoMLSim · 2-D linear Poissonconvergence speedImproved
increase out-of-distribution source Gaussians up to 60CoMLSim and baselines · linear and non-linear PoissonerrorHurt
scale grid from 1024^2 up to 8192^2 without retrainingCoMLSim · 2-D linear PoissonerrorNo clear effect

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