Offshore jacket structures play a key role in renewable energy by supporting offshore wind turbines (OWTs). This study presents the development and application of advanced meta-models for efficient prediction of fatigue damage in jacket joints of 25 MW OWTs. Although meta-models have become state-of-the-art for fatigue assessment of conventional OWTs (typically 5–15 MW), there remains a need to validate their applicability to next-generation turbines with mega structures and capacities over 20 MW. For the first time, in this study, the performance of such meta-models has been tested and validated using data generated within a systematic framework. This addresses a critical knowledge gap as the industry transitions to unprecedented turbine capacities. The investigation focused on two representative joints: the most critical and the mudline joints. The integration of aeroelastic, hydrodynamic, and soil-structure interactions within a methodological framework enables the training of Kriging-based meta-models on high-fidelity simulation data, ensuring rapid and accurate predictions. A parametric analysis is conducted with respect to key environmental drivers, including wind speed, significant wave height, peak period, turbulence intensity, and wind–wave misalignment. The predictive performance validation demonstrates the effectiveness of meta-models even at these large scales. A rigorous benchmark against an established 5 MW OWT meta-model reveals pronounced scaling effects. The results indicate that as the turbine size increases, the wave-induced loading becomes the predominant fatigue driver for the jacket, surpassing wind speed effects. This challenges existing design assumptions for large-scale turbine jackets. The findings of this study represent a significant advancement, as they demonstrate, for the first time, the potential of meta-models to facilitate rapid, data-driven fatigue assessments of offshore mega-jacket designs. This advancement paves the way for enhanced reliability and efficiency in jacket design, optimization, and operational monitoring for future high-capacity wind turbines. • First Kriging meta-model validated for fatigue analysis of 25 MW offshore jackets. • Wave height surpasses wind speed as the dominant fatigue driver at large scales. • Meta-Model configurations transfer effectively from 5 MW to 25 MW turbines. • Nonlinear scaling effects identified between turbine size and fatigue behavior. • Enables rapid, data-driven fatigue assessment for offshore megastructures.
Moattari et al. (Fri,) studied this question.