AI Paper Atlas

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

LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite

Artur Toshev, Gianluca Galletti, Fabian Fritz, Stefan Adami, Nikolaus A. Adams

NeurIPS 2023 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed operator learning · 1 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 GNS-10-64 on 1% to 100% of the training data (ablation)GNS-10-64 · All LagrangeBench datasetsposition MSEImproved
more training data (beyond ~10k frames) (ablation)GNS-10-64 · 2D RPF and other datasetsposition MSENo clear effect
more training data (ablation)GNS-10-64 · Dam breakposition MSEImproved
higher SEGNN tensor product order (L=2 vs L=1) (ablation)SEGNN-10-64 · LagrangeBench datasetsaccuracy vs runtime: 29.7 -> 86.0Mixed
use GNS instead of SEGNN on problems with boundaries (LDC, DAM)baseline GNNs · 2D/3D LDC and DAMMSE20Improved
use SEGNN (equivariant) instead of GNS on pure fluid problems (TGV, RPF)baseline GNNs · TGV, 3D RPFMSE20: 5.2e-3Improved
EGNN architecture instead of GNS or SEGNNbaseline GNNs · LagrangeBench datasetstraining stabilityHurt
PaiNN extended to general vectorial inputs instead of GNS or SEGNNbaseline GNNs · LagrangeBench datasetslossHurt
non-periodic displacement functions instead of periodic in EGNN (ablation)EGNN-5-128 · inference time 2D (3.2K) and 3D (8.1K)inference ms: 50.0 -> 3.49 (2D); 206 -> 15.1 (3D)Improved
jaxmd_scan serialized neighbor list instead of jaxmd_vmap (ablation)neighbor search · A6000 48GB memory limitmax particles that fit in memory: 1M -> 3.3MImproved
matscipy CPU neighbor list instead of GPU JAX-MD (ablation)SEGNN on 2D DAM · training speedtraining time: +50%Hurt
deeper/wider GNS (5-64 -> 10-64 -> 10-128) (ablation)GNS · 2D inference (3.2K particles)inference ms: 2.05 -> 3.89 -> 6.66Hurt

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