Surface weather parameters detain high socioeconomic impact and strategic insights for all users,in all domains(aviation,marine traffic,agriculture,etc.).However,those parameters were mainly predicted by using determi...Surface weather parameters detain high socioeconomic impact and strategic insights for all users,in all domains(aviation,marine traffic,agriculture,etc.).However,those parameters were mainly predicted by using deterministic numerical weather prediction(NWP)models that include a wealth of uncertainties.The purpose of this study is to contribute in improving low-cost computationally ensemble forecasting of those parameters using analog ensemble method(AnEn)and comparing it to the operational mesoscale deterministic model(AROME)all over the main airports of Morocco using 5-yr period(2016-2020)of hourly datasets.An analog for a given station and forecast lead time is a past prediction,from the same model that has similar values for selected predictors of the current model forecast.Best analogs verifying observations form AnEn ensemble members.To picture seasonal dependency,two configurations were set;a basic configuration where analogs may come from any past date and a restricted configuration where analogs should belong to a day window around the target forecast.Furthermore,a new predictors weighting strategy is developed by using machine learning techniques(linear regression,random forest,and XGBoost).This approach is expected to accomplish both the selection of relevant predictors as well as finding their optimal weights,and hence preserve physical meaning and correlations of the used weather variables.Results analysis shows that the developed AnEn system exhibits a good statistical consistency and it significantly improves the deterministic forecast performance temporally and spatially by up to 50%for Bias(mean error)and 30%for RMSE(root-mean-square error)at most of the airports.This improvement varies as a function of lead times and seasons compared to the AROME model and to the basic AnEn configuration.The results show also that AnEn performance is geographically dependent where a slight worsening is found for some airports.展开更多
文摘Surface weather parameters detain high socioeconomic impact and strategic insights for all users,in all domains(aviation,marine traffic,agriculture,etc.).However,those parameters were mainly predicted by using deterministic numerical weather prediction(NWP)models that include a wealth of uncertainties.The purpose of this study is to contribute in improving low-cost computationally ensemble forecasting of those parameters using analog ensemble method(AnEn)and comparing it to the operational mesoscale deterministic model(AROME)all over the main airports of Morocco using 5-yr period(2016-2020)of hourly datasets.An analog for a given station and forecast lead time is a past prediction,from the same model that has similar values for selected predictors of the current model forecast.Best analogs verifying observations form AnEn ensemble members.To picture seasonal dependency,two configurations were set;a basic configuration where analogs may come from any past date and a restricted configuration where analogs should belong to a day window around the target forecast.Furthermore,a new predictors weighting strategy is developed by using machine learning techniques(linear regression,random forest,and XGBoost).This approach is expected to accomplish both the selection of relevant predictors as well as finding their optimal weights,and hence preserve physical meaning and correlations of the used weather variables.Results analysis shows that the developed AnEn system exhibits a good statistical consistency and it significantly improves the deterministic forecast performance temporally and spatially by up to 50%for Bias(mean error)and 30%for RMSE(root-mean-square error)at most of the airports.This improvement varies as a function of lead times and seasons compared to the AROME model and to the basic AnEn configuration.The results show also that AnEn performance is geographically dependent where a slight worsening is found for some airports.
