AI Paper Atlas

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

Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation

Siqi Ding, Zitong Zhang, Shi Guoyang, Xingyu Li, Xiang Gu, Yanan Xu, Huasheng Xie, Hanyue Zhao, YUEJIANG SHI, Tianyuan Liu

ICML 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural operators for general geometries · 0 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
use KAN regressor instead of coordinate MLP (ablation)coordinate network · GSE pilot 4D IID testMean L2(psi) error (%): 4.93 -> 0.34Improved
use Transformer trunk instead of MLP, FNO or CNN trunk with KAN regressor (ablation)TKNO · GSE pilot 4D IID testMean L2(psi) error (%): 0.54 / 0.36 / 0.30 -> 0.25Improved
CNN trunk gives low pointwise error but large PDE residual (ablation)C-K · GSE pilot 4D IID testMAE(PDE): 1.23 -> 5.23 (vs TKNO)Hurt
train with physics-only losses instead of data-only (ablation)TKNO · GSE pilot 4DL2(psi) error (%): 0.25 -> 0.62Hurt
increase sparse anchors from 10 to 100 points (ablation)Physics-anchored TKNO · GSE pilot 4DL2(psi) error (%): 0.75 -> 0.59Improved
increase sparse anchors from 100 to 1000 points (ablation)Physics-anchored TKNO · GSE pilot 4DMSE(PDE): L2 0.59 -> 0.52; MSE(PDE) 0.011 -> 0.023Mixed
add data anchors to PDE constraints (physics-anchored vs physics-only) (ablation)TKNO · GSE 10D joint OODMean L2(psi) error (%): 42.77 -> 11.44Improved
add PDE constraints to data supervision (physics-anchored vs data-only) (ablation)TKNO · GSE 10D Joint Any-OODp99 L2(psi) error (%): 53.66 -> 44.12Improved
add PDE constraints to data supervision (ablation)TKNO · GSE 10D isolated Shape OODp99 L2(psi) error (%): 52.25 -> 33.16Improved
add PDE constraints to data supervision (ablation)TKNO · GSE 10D IID holdoutMean L2(psi) error (%): 0.24 -> 0.59Hurt
add PDE constraints to data supervision (ablation)TKNO · GSE 10D isolated Profile OODMean L2(psi) error (%): 5.80 -> 7.69Hurt
add data supervision to physics-only training (ablation)TKNO · GSE 10D joint OODbranch-scale failure rate: approximately 12% -> below 0.2%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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