AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

MMGP: a Mesh Morphing Gaussian Process-based machine learning method for regression of physical problems under nonparametrized geometrical variability

Fabien Casenave, Brian Staber, Xavier Roynard

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Machine learning for physical simulation · 2 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
replace best GNN baseline (GCNN) with MMGPGCNN · Rotor37 mrelative RMSE: 4.4e-3 -> 5.0e-4Improved
MMGP vs best GNN baseline (MGN) on the hard plasticity scalarMMGP · Tensile2d p_maxrelative RMSE: 2.7e-1 -> 6.6e-1Mixed
replace best GNN baseline (MGN) with MMGPMGN · AirfRANS C_Drelative RMSE: 4.9e-2 -> 3.3e-2Improved
replace best GNN baseline (MGN) with MMGPMGN · AirfRANS C_Lrelative RMSE: 2.4e-1 -> 8.0e-3Improved
replace best GNN baseline (GCNN) with MMGPGCNN · Tensile2d v_maxrelative RMSE: 4.4e-2 -> 5.0e-3Improved
MMGP vs MGN training timeMGN · Rotor37training time: 13 h 14 min -> 2 min 49 sImproved
MMGP vs GCNN training timeGCNN · Rotor37training time: 24 h -> 2 min 49 sImproved
MMGP vs GCNN training timeGCNN · Tensile2dtraining time: 1 h 25 min -> 1 min 38 sImproved
MMGP vs MGN training timeMGN · AirfRANStraining time: 5 h 00 min -> 5 min 47 sImproved
MMGP vs GCNN Q2 on hardest field pGCNN · Tensile2d pQ2: 0.5691 -> 0.7785Improved
MMGP prediction intervals coverage at nominal 95%MMGP · AirfRANS C_DPICP: 93.5No clear effect
MMGP vs MGN on Rotor37 eta Q2MGN · Rotor37 etaQ2: 0.5551 -> 0.9979Improved

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