TITLE:
Spatio-Temporal Modelling of Air Pollution Using Earth Observation and Deep Learning Techniques: A Case Study of Nairobi Metropolitan Area
AUTHORS:
Samuel Orwa Odoyo, Solomon Mwanjele Mwagha, Arthur W. Sichangi
KEYWORDS:
Air Pollution, Nairobi, CNN, LSTM, NeuralProphet, Sentinel-5P, Deep Learning, Forecasting
JOURNAL NAME:
Journal of Geoscience and Environment Protection,
Vol.14 No.5,
May
28,
2026
ABSTRACT: Aims: This study models key air pollutants (PM10, CO, HCHO, CH4, NO2, O3, SO2) across the Nairobi Metropolitan Area using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) framework for the years 2019-2024, and forecasts their 2025 levels using the NeuralProphet time series model. Random Forest Regression Kriging was incorporated to refine spatial outputs. Study design: Retrospective modelling and forecasting study based on multi-source Earth Observation and meteorological datasets, validated with Flow 2 Sensor data. Place and Duration of Study: Nairobi Metropolitan Area; January 2019-December 2025. Methodology: Pollution data were sourced from Sentinel-5P, with PM10 derived using aerosol as a proxy. Weather variables came from MERRA-2 reanalysis. LULC was extracted from Sentinel-2 and SRTM data gave us elevation inputs. CNN extracted spatial features while LSTM captured temporal patterns. NeuralProphet handled future forecasting, and Regression Kriging improved spatial continuity. Results: CNN + LSTM model accurately captured spatio-temporal pollution trends between 2019 and 2024, with low validation MAE (0.0456) and RMSE (0.20), while the NeuralProphet model preserved spatial patterns and seasonal dynamics in 2025 forecasts with a validation MAE (0.16) and RMSE (0.20). However, both models underestimated ground-level PM10 and NO2 concentrations. Random Forest Regression Kriging was incorporated to refine spatial outputs, with pollutant specific outcomes. For NO2, kriging marginally reduced R2 from 0.998 to 0.996 but improved spatial autocorrelation (Moran’s I = 0.994) and reduced RMSE to 1.302 μg/m3. For PM10, however, kriging degraded accuracy (R2 declined from 0.915 to 0.782, RMSE increased to 13.805 μg/m3), reflecting the pollutant’s high spatial variability and episodic nature, which limits the suitability of geostatistical interpolation for particulate matter. Conclusion: The study demonstrates the effectiveness of combining satellite data and deep learning in modelling and forecasting urban air pollution. CNN + LSTM and NeuralProphet provide a robust, scalable alternative to sparse ground monitoring networks, supporting urban air quality management in rapidly growing African cities. Key findings: 1) CNN + LSTM achieved validation MAE of 0.0456 and RMSE of 0.20; 2) NeuralProphet forecasts preserved seasonal dynamics (MAE_val = 0.16); 3) Kriging improved NO2 spatial accuracy but degraded PM10 due to episodic variability.