Skillful bias correction of offshore near-surface wind speed and wind direction forecasting based on a multi-task machine learning model

Dataset 1. observation data over 14 weather stations Variables: hourly near-surface 2-min average wind speed, wind direction 2. ECMWF-IFS forecast data over 14 weather stations Variables: hourly predictors at surface level and upper level in next 48 hours (shown in Table 1. and Table 2.) Table 1. ECMWF-IFS forecast data at surface level Predictors Abbreviation Unit Temperature at 2 m 2t ℃ Sea surface temperature sst ℃ Surface skin temperature skt ℃ Dewpoint temperature at 2 m 2d ℃ Convective precipitation in the past hour cp mm Surface pressure sp hPa Mean sea level pressure msl hPa Zonal component of wind speed at 10 m 10u m s-1 Meridional component of wind speed at 10 m 10v m s-1 Wind speed at 100 m 10ws m s-1 Zonal component of wind speed at 100 m 100u m s-1 Meridional component of wind speed at 100 m 100v m s-1 Wind speed at 100 m 100ws m s-1 Table 2. ECMWF-IFS forecast data at upper level Predictors Abbreviation Unit Relative humidity at xxx hPa r_Lxxx % Temperature at xxx hPa t_Lxxx ℃ Vertical velocity of wind at xxx hPa w_Lxxx Pa s-1 Zonal component of wind at xxx hPa u_Lxxx m s-1 Meridional component of wind at xxx hPa v_Lxxx m s-1 Wind speed at xxx hPa ws_Lxxx m s-1 Wind direction at xxx hPa wd_Lxxx ° 3. key variables constructed by feature engineering ① statistics values (maximum, minimum, mean and variance) of key variables (2t, 10u, 10v and 10ws) from ECMWF-IFS model during the next 48 hours (short-term) and history 3-yr period (January 2020–December 2022, long-term) ② short-term variance of msl and sp ③ short-term and long-term deviations of key variables (2t, 10u, 10v and 10ws) Model 1. RF_model (Single-Task Learning Model) 2. LighGBM_model (Single-Task Learning Model) 3. XGBoost_model (Single-Task Learning Model) 4. TabNet_STL_model (Single-Task Learning Model) 5. TabNet_MTL_model (Multi-Task Learning Model) Scripts Python program scripts used for 1. Model training on training datasets2. Model evaluation on test datasets Figures Figures corresponding to Python program output