Abstract The design phase of offshore renewable energy systems requires considering numerous design load cases to meet standards. Long-term fatigue assessment, often the most time-consuming aspect, demands thousands of time-domain simulations to capture the combined effects of environmental conditions. This process becomes computationally expensive, contributing to the already high Levelized Cost of Energy (LCOE) for offshore renewables. To alleviate this computational burden, this study applies the K-means clustering technique, significantly reducing the number of environmental cases while maintaining fatigue estimation accuracy. A sensitivity analysis is conducted based on the number of clusters and statistical metrics to validate the approach. Results show that K-means effectively captures key resource characteristics and accurately estimates fatigue damage with 1000 clusters. This reduces the number of cases for fatigue analysis significantly, favorably impacting computational costs and enhancing the feasibility of large-scale studies in offshore renewable energy design.