Shikwambana, LSebake, MMolefe, MHavenga, HMbatha, Nkanyiso B2026-07-282026-07-282026-062073-4433https://doi.org/10.3390/atmos17060610http://hdl.handle.net/10204/14868This study applies a Long Short-Term Memory (LSTM) model to predict key air pollutants, i.e., sulphur dioxide (SO2), nitrogen dioxide (NO2), and particulate matter (PM2.5), as well as the Air Quality Index (AQI) across South Africa using satellite-derived observations. The analysis focuses on comparing original pollutant fields with model-generated predictions for two consecutive days, highlighting both spatial patterns and predictive performance. Results reveal a persistent and intense pollution hotspot over the Mpumalanga Highveld, driven by coal-fired power generation and industrial activities. Elevated pollutant concentrations in this region translate into AQI levels ranging from Unhealthy to Very Unhealthy, while most other parts of the country remain within the Good category. Spatial comparison between original and predicted fields shows strong agreement, with only minor deviations in areas characterized by steep emission gradients and localized plumes. Quantitative evaluation using RMSE (0.020390) and MSE (0.000416) confirms the high accuracy of the predictive model, with error values remaining extremely low across all pollutants and AQI outputs. PM2.5 exhibits the smallest errors (MSE = 4.230169 × 10−6), while slightly higher values for SO2 (MSE = 2.628 × 10−4) and NO2 (MSE = 1.39541 × 10−4) reflect the difficulty of capturing sharp spatial transitions associated with pointsource emissions. Despite these localized discrepancies, the model demonstrates robust skill in replicating both pollutant magnitudes and AQI classifications. Overall, the findings indicate that machine-learning approaches offer a reliable, high-resolution tool for air-quality prediction in South Africa and have strong potential for supporting operational forecasting, exposure assessment, and environmental policy development.FulltextenAir quality predictionsSatellite ObservationsLong Short-Term MemoryLSTMConvolutional neural networksCNNAtmospheric pollutantsRemote sensingArticlen/a