Offshore wind power

as a key component of clean energy

has experienced rapid development in recent years. However

achieving high-temporal resolution and long-term assessments of offshore wind resources remains challenging due to limitations in marine meteorological monitoring capabilities and the high computational complexity of Earth System Model (ESM). To address this issue

this paper proposes a temporal flow matching model that integrates historical meteorological monitoring data to perform bias correction and temporal resolution enhancement on ESM simulations. The method employs differential equations to model the continuous transformation path from low-resolution to high-resolution data and fits the velocity field during the probability distribution transformation to characterize the target data distribution. Using ERA5 reanalysis data combined with offshore meteorological buoy observations for simulation and validation

the results demonstrate that the proposed method can effectively simulate sub-hourly wind speed fluctuations and capture the uncertainty in wind energy resources. This work provides a novel technical pathway for offshore wind resource assessment.