Predicting Particulate Matter (PM10) Levels in Morocco: A 5-Day Forecast Using the Analog Ensemble Method.

Abstract

Accurate prediction of Particulate Matter (\({PM}_{10}\)) levels, an indicator of natural pollutants such as those resulting from dust storms, is crucial for public health and environmental planning. This study aims to provide accurate forecasts of \({PM}_{10}\) over Morocco for five days. The Analog Ensemble (AnEn) and the Bias Correction (AnEnBc) techniques were employed to post-process \({PM}_{10}\) forecasts produced by the Copernicus Atmosphere Monitoring Service (CAMS) global atmospheric composition forecasts, using CAMS reanalysis data as a reference. The results show substantial prediction improvements: the Root Mean Square Error (RMSE) decreased from 63.83 \(\mu g/{m}^{3}\) in the original forecasts to 44.73 \(\mu g/{m}^{3}\) with AnEn and AnEnBc, while the Mean Absolute Error (MAE) reduced from 36.70 \(\mu g/{m}^{3}\) to 24.30 \(\mu g/{m}^{3}\). Additionally, the coefficient of determination (\({R}^{2}\)) increased more than twofold from 29.11–65.18%, and the Pearson correlation coefficient increased from 0.61 to 0.82. This is the first use of this approach for Morocco and the Middle East and North Africa and has the potential for translation into early and more accurate warnings of \({PM}_{10}\) pollution events. The application of such approaches in environmental policies and public health decision making can minimize air pollution health impacts.