AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset Generation

Jan-Hendrik Ewers, Santiago Cadena, Nicolò Foppiani, Andrea Merlo

NeurIPS 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Machine learning for physical simulation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces CoilStellaration, a dataset and benchmark for engineering-aware stellarator coil set generation, aimed at letting machine learning methods design electromagnetic coils for fusion devices.

Problem

Designing electromagnetic coils that produce a stellarator's confining magnetic field is the key factor in whether the device can be practically engineered and built cost-effectively, and existing approaches lack a standard engineering-aware dataset and benchmark for coil set generation.

Approach

A dataset and benchmark for stellarator coil set generation that incorporates engineering considerations, so that coil designs can be evaluated for practical manufacturability and cost, not only magnetic field quality.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
ensemble five networks instead of a single model (ablation)PerCoilMLP · variable-shape trackmean score S: 0.082 -> 0.137Improved
ensemble five networks instead of a single model (ablation)ResMLP · fixed-shape trackmean score S: 0.076 -> 0.133Improved
use residual backbone instead of plain MLP (ablation)MLP · fixed-shape trackstrict feasibility: 2.6 -> 3.8 (single); 2.7 -> 4.4 (ensemble)Improved
use residual backbone instead of plain MLP (ablation)MLP · fixed-shape trackmean score S: 0.067 -> 0.076No clear effect
share one model across topologies (variable-shape) instead of fixed-shape specialist (ablation)EnsemblePerCoilMLP · fixed-shape subsetmean score S: 0.133 -> 0.18Improved
tighter field-error requirement tier (ablation)all baselines · requirement tierstrict feasibility: loose 7-12% -> tight 0%Hurt
initialize DESC optimization with learned coilset instead of REGCOIL (ablation)DESC · tight-tier instances, 500 iterationsstrict feasibility: 18% -> 27%Improved
initialize DESC optimization with learned coilset instead of REGCOIL (ablation)DESC · tight-tier instances, 500 iterationsmean score S: 0.83 (REGCOIL) vs 0.76 (learned)Hurt
initialize DESC optimization with learned coilset instead of REGCOIL (ablation)DESC · tight-tier instances, early iterations (up to 200)mean score SImproved
initialize DESC optimization with learned coilset instead of REGCOIL (ablation)DESC · tight-tier instances, 1000 iterationsstrict feasibility: 26% -> 25%No clear effect
learned start versus REGCOIL start on coil-coil spacing (ablation)DESC · tight-tier instances, 1 iterationcoil-coil spacing requirement met: 92% -> 38%Hurt
learned start versus REGCOIL start on coil-plasma spacing (ablation)DESC · tight-tier instances, 1 iterationcoil-plasma spacing requirement met: 10% -> 58%Improved

Experimental setup

Benchmarks: CoilStellaration

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