Benchmark RadarFLOATBench
FLOATBench is a tabular benchmark for surrogate modeling of tower fatigue in 22 MW floating offshore wind turbines. It provides 582,120 per-section fatigue damage labels from OpenFAST simulations across three tower geometries, with regime-aware splits and three evaluation protocols (random, within-tower regime-aware, cross-tower transfer).
- Released
- 2026-05-25
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Previously, no shared benchmark existed for FOWT fatigue surrogates, hindering comparison. FLOATBench provides a standardized dataset and protocol, enabling fair evaluation and highlighting regime-aware performance differences.
Motivation
Most of the world's offshore wind resource lies in waters too deep for fixed-bottom foundations, making floating offshore wind turbines (FOWTs) essential for deep-water deployment.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.