1. MMC
  2. All Volumes and Issues
  3. Volume 13, Number 2, 2026
  4. Development of Hybrid ARIMA-LSTM and Prophet-LSTM Models for Air Quality Forecasting in the Tangier Region

Development of Hybrid ARIMA-LSTM and Prophet-LSTM Models for Air Quality Forecasting in the Tangier Region

MMC.
2026;
Volume 13, Number 2
: pp. 385–394
https://doi.org/10.23939/mmc2026.02.385
Received: July 25, 2025
Revised: May 10, 2026
Accepted: May 12, 2026

Marrakchi N., Bergam A., Fakhouri H.  Development of Hybrid ARIMA-LSTM and Prophet-LSTM Models for Air Quality Forecasting in the Tangier Region.  Mathematical Modeling and Computing. Vol. 13, No. 2, pp. 385–394 (2026)

Authors:
  1. N. Marrakchi
  2. A. Bergam
  3. H. Fakhouri
1
SMAD, FPL, Abdelmalek Essaadi University
2
SMAD, FPL, Abdelmalek Essaadi University
3
SMAD, FPL, Abdelmalek Essaadi University

Accurately predicting tropospheric ozone (O$_3$) levels is essential for improving air quality in Tangier, given its significance as a major atmospheric pollutant.  In this study, we propose a hybrid forecasting approach that combines ARIMA-LSTM and Prophet-LSTM models to improve both the accuracy and robustness of ozone concentration predictions.  The method leverages the strengths of ARIMA and Prophet in capturing linear trends and seasonal variations, while leveraging the ability of LSTM networks to model nonlinear dynamics and long-term dependencies.  Comparative analyses show that the Prophet-LSTM combination delivers the most reliable performance, providing improved forecasting accuracy.  This hybrid model is particularly effective in identifying pollution peaks, with an agreement index reaching $d=0.99$.

air quality
Ozone (O3)
ARIMA
FB-Prophet
LSTM
hybrid models
  1. Samadi A., Achelhi H.  Industry 4.0 in The Economic Activity Zones in Morocco: Tangier-Tetouan-Alhoceima Region Case. International Journal of Accounting Finance Auditing Management and Economics.  2 (6–1), 327–338 (2021).
  2. Zhang B., Song C., Li Y., Jiang X.  Spatiotemporal prediction of O$_3$ concentration based on the KNN-Prophet-LSTM model.  Heliyon.  8 (11), e11670 (2022).
  3. Lim C. C., Hayes R. B., Ahn J., Shao Y., Silverman D. T., Jones R. R., Garcia C., Bell M. L., Thurston G. D.  Long-term exposure to ozone and cause-specific mortality risk in the United States.  American journal of respiratory and critical care medicine.  200 (8), 1022–1031 (2019).
  4. Zhang G. P., Kline D. M.  Quarterly time-series forecasting with neural networks.  IEEE Transactions on Neural Networks.  18 (6), 1800–1814 (2007).
  5. Weiss M., Bonnel P., Kühlwein J., et al.  Will Euro 6 reduce the NO$_x$ emissions of new diesel cars? – Insights from on-road tests with Portable Emissions Measurement Systems (PEMS).  Atmospheric Environment.  62, 657–665 (2012).
  6. Tamas W. W., Notton G., Paoli C., Nivet M. L., Voyant C.  Hybridization of air quality forecasting models using machine learning and clustering: An original approach to detect pollutant peaks.  Aerosol and Air Quality Research.  16 (2), 405–416 (2016).
  7. Chanchaichujit J., Pham Q. C., Tan A.  Sustainable supply chain management: A literature review of recent mathematical modelling approaches.  International Journal of Logistics Systems and Management.  33 (4), 467–496 (2019).
  8. Garg N., Soni K., Saxena T., Maji S.  Applications of Autoregressive integrated moving average (ARIMA) approach in time-series prediction of traffic noise pollution.  Noise Control Engineering Journal.  63 (2), 182–194 (2015).
  9. Comrie A. C.  Comparing neural networks and regression models for ozone forecasting.  Journal of the Air \& Waste Management Association.  47 (6), 653–663 (1997).
  10. Tamas W., Notton G., Paoli C., Voyant C., Nivet M. L., Balu A.  Urban ozone concentration forecasting with artificial neural network in Corsica.  Modelling in Civil Environmental Engineering.  10 (1), 29–37 (2014).
  11. Alon I., Qi M., Sadowski R. J.  Forecasting aggregate retail sales:: a comparison of artificial neural networks and traditional methods.  Journal of Rretailing and Consumer Services.  8 (3), 147–156 (2001).
  12. Bose A., Chowdhury I. R.  Towards cleaner air in Siliguri: A comprehensive study of PM$_{2.5}$ and PM$_{10}$ through advance computational forecasting models for effective environmental interventions.  Atmospheric Pollution Research.  15 (2), 101976 (2024).
  13. Sachdeva S., Kaur R., Kimmi, Singh H., Aggarwal K., Kharb S.  Meteorological AQI and pollutants concentration-based AQI predictor.  International Journal of Environmental Science and Technology.  21, 4979–4996 (2024).
  14. Ensafi Y., Amin S. H., Zhang G., Shah B.  Time-series forecasting of seasonal items sales using machine learning – A comparative analysis.  International Journal of Information Management Data Insights.  2 (1), 100058 (2022).
  15. Lazy Programmer Inc., Lazy Programmer Team.  Deep Learning: Recurrent Neural Networks in Python, LSTM, GRU, and more RNN machine learning architectures in Python and Theano (2016).
  16. Willmott C. J., Robeson S. M., Matsuura K.  A refined index of model performance.  International Journal of climatology.  32 (13), 2088–2094 (2012).