Shanghai Innovation Institute provides a dataset of stellarator configurations grouped by field period count. Each sample includes Fourier boundary coefficients, the number of field periods (nfp), and nine VMEC evaluation metrics. The dataset was last updated on May 10, 2026.
Use Cases
- Train machine learning models to predict VMEC metrics based on Fourier boundary coefficients.
- Analyze the relationship between field period count (nfp) and stellarator configuration performance.
- Benchmark optimization algorithms for designing stellarator magnetic confinement systems.
Strengths
- Each sample includes nine VMEC evaluation metrics.
- Data is grouped by the number of field periods (nfp).
- All fields are guaranteed to be non-null.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
Provenance
- Source
- SII-AI4Fusion
- Freshness
- Last updated 2026-05-10 23:25:59; freshness should be verified.