A Comparative Analysis of NNAR and LSTM Models for Short-Term COVID-19 Forecasting in Saudi Arabia
Article Sidebar
Main Article Content
Abstract
The COVID-19 pandemic has posed an ongoing challenge for public health systems around the globe. Accurate forecasting of daily confirmed COVID-19 cases in Saudi Arabia has remained critical for informed planning and timely interventions. This research explores and compares the predictive performance of two artificial neural network models—Nonlinear Autoregressive Neural Network (NNAR) and Long Short-Term Memory (LSTM)—applied to Saudi Arabia’s COVID-19 case data from March 2020 through December 2021. Using standard evaluation metrics, including MAE, RMSE, MAPE, and Theil’s U, the study demonstrates that the NNAR model provides slightly more stable and accurate predictions in short-term horizons than LSTM. While LSTM models are known for capturing complex temporal patterns, our findings suggest that NNAR may offer a more robust option in volatile epidemiological conditions. These insights contribute to the growing field of epidemic forecasting and provide practical considerations for health policymakers in the region.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI: https://doi.org/10.1162/neco.1997.9.8.1735
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175. DOI: https://doi.org/10.1016/S0925-2312(01)00702-0
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice (2nd ed.). OTexts. https://otexts.com/fpp2/
Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (2008). Time Series Analysis: Forecasting and Control (4th ed.). Wiley. DOI: https://doi.org/10.1002/9781118619193
Benvenuto, D. et al. (2020). Application of the ARIMA model on the COVID-19 epidemic dataset. Data in Brief, 29, 105340. DOI: https://doi.org/10.1016/j.dib.2020.105340
Liu, D. et al. (2021). Forecasting COVID-19 dynamics and interventions in the US using deep learning. Nature Communications, 12, 1–10. DOI: https://doi.org/10.1038/s41467-021-22457-w
Shastri, S. et al. (2020). Time series forecasting of COVID-19 using deep learning models. Chaos, Solitons & Fractals, 140, 110227. DOI: https://doi.org/10.1016/j.chaos.2020.110227
Ribeiro, M. H. D. M. et al. (2020). Short-term forecasting COVID-19 cumulative confirmed cases. Chaos, Solitons & Fractals, 135, 109853. DOI: https://doi.org/10.1016/j.chaos.2020.109853
Chimmula, V. K. R., & Zhang, L. (2020). Time series forecasting of COVID-19 in Canada using LSTM. Chaos, Solitons & Fractals, 135, 109864. DOI: https://doi.org/10.1016/j.chaos.2020.109864
WHO Coronavirus Dashboard. https://covid19.who.int
Saudi Ministry of Health COVID-19 Dashboard. https://www.emro.who.int/right-teasers/saudi-arabia/sau-statistics.html
Iqbal, M. W. et al. (2020). Prediction of COVID-19 using ARIMA and LSTM models. SN Computer Science, 2(5), 1–7. DOI: https://doi.org/10.3390/math10214001
Rustam, F. et al. (2020). COVID-19 future forecasting using machine learning models. IEEE Access, 8, 101489–101499. DOI: https://doi.org/10.1186/s12874-022-01755-x
Bandara, K. et al. (2020). Forecasting COVID-19 cases using time series models and ML. BMC Medical Informatics and Decision Making, 20, 341.
DOI: https://doi.org/10.1186/s12911-020-01395-3
Petropoulos, F., & Makridakis, S. (2020). Forecasting COVID-19. PLOS ONE, 15(3), e0231236. DOI: https://doi.org/10.1371/journal.pone.0231236
Chakraborty, T., & Ghosh, I. (2020). Real-time forecasts and risk assessment of COVID-19. Chaos, Solitons & Fractals, 135, 109850. DOI: https://doi.org/10.1016/j.chaos.2020.109850
Sagheer, A., & Kotb, M. (2019). Forecasting petroleum production with LSTM. Neurocomputing, 323, 203–213. DOI: https://doi.org/10.1016/j.neucom.2018.09.082
Salgotra, R. et al. (2020). Forecast of COVID-19 in India using genetic programming. Chaos, Solitons & Fractals, 138, 109945. DOI: https://doi.org/10.1016/j.chaos.2020.109945
Kim, S. et al. (2021). Deep learning for real-time COVID-19 forecasting. Journal of Biomedical Informatics, 117, 103773. DOI: https://doi.org/10.1016/j.neucom.2022.09.005
Khan, M. A. et al. (2022). Ensemble learning for COVID-19 prediction. Computer Methods and Programs in Biomedicine, 214, 106584. DOI: https://doi.org/10.3390/s22062224
Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37–45. DOI: https://doi.org/10.1080/00031305.2017.1380080
Al Zahrani, S., Al Sameeh, F. A. R., Musa, A. C. M., & Shokeralla, A. A. (2020). Forecasting diabetes patients attendance at Al-Baha hospitals using autoregressive fractional integrated moving average (ARFIMA) models. Journal of Data Analysis and Information Processing, 8, 183–194. DOI: https://doi.org/10.4236/jdaip.2020.83011
Wu, J. T. et al. (2020). Forecasting COVID-19 spread. The Lancet, 395(10225), 689–697. DOI: https://doi.org/10.1016/S0140-6736(20)30260-9
Wang, P. et al. (2021). Forecasting COVID-19 with Prophet model. Scientific Reports, 11, 20513. DOI: https://doi.org/10.1155/2022/1556025
Tuli, S. et al. (2020). Predicting COVID-19 growth using ML and cloud. Scientific Reports, 10, 21061. DOI: https://doi.org/10.1016/j.iot.2020.100222
Bezerra, A. K. L., & Santos, É. M. C. (2020). Prediction of COVID-19 in Sudan with ARIMA & Holt-Winters. International Journal of Development Research, 10(8), 39408–39413. https://www.journalijdr.com/sites/default/files/issue-pdf/19811.pdf
Hazarika, B. B. et al. (2022). Deep learning for COVID-19 forecasting: Review. Computer Methods and Programs in Biomedicine, 214, 106585. DOI: https://doi.org/10.1016/j.cmpb.2021.106585
Raza, S. E. A. et al. (2021). Comparative analysis of ARIMA and LSTM in Gulf. J. King Saud Univ. Comput. Inf. Sci. DOI: https://doi.org/10.1016/j.jksuci.2021.03.005
Shokeralla, A. A. et al. (2023). The effect of symptoms on survival time of COVID-19 patients in Sudan. International Journal of Statistics in Medical Research, 12, 249–256. DOI: https://doi.org/10.6000/1929-6029.2023.12.29
Daqqa, I. et al. (2024). Predictive modeling of breast cancer incidence. Journal of Statistics Applications & Probability, 14(2), 183–189. DOI: https://doi.org/10.18576/jsap/140204
Fath-Elrhman, E. I. et al. (2020). Modeling Sudan’s inflation rate using neural networks. International Journal of Engineering, Science and Mathematics, 9(10), 1–11. https://www.indianjournals.com/ijor.aspx?target=ijor:ijesm&volume=9&issue=10&article=001&type=pdf
Ghosh, I., & Chakraborty, T. (2020). A deep learning-based framework to predict COVID-19 outbreak. Neural Networks, 132, 294–302. DOI: https://doi.org/10.1016/j.neunet.2020.09.004
Yang, Z., Zeng, Z., Wang, K., Wong, S.-S., Liang, W., Zanin, M., ... & He, J. (2020). Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions. Journal of Thoracic Disease, 12(3), 165–174. DOI: https://doi.org/10.21037/jtd.2020.02.64
Khosravi, A., Nahavandi, S., Creighton, D., & Atiya, A. F. (2011). Comprehensive review of neural network-based prediction intervals and new advances. IEEE Transactions on Neural Networks, 22(9), 1341–1356. DOI: https://doi.org/10.1109/TNN.2011.2162110
Gu, Q., Ding, Y., & Han, J. (2008). Learning representative graphical structures for time series modeling. IEEE Transactions on Knowledge and Data Engineering, 20(3), 376–392. DOI: https://doi.org/10.1109/TKDE.2007.190712
Ceylan, R. (2020). Estimation of COVID-19 prevalence in Italy, Spain, and France. Chaos, Solitons & Fractals, 138, 109924. DOI: https://doi.org/10.1016/j.chaos.2020.109924
Deb, S., & Majumdar, M. (2021). A time series method for modeling and forecasting the number of COVID-19 cases. Heliyon, 7(3), e06504. DOI: https://doi.org/10.1016/j.heliyon.2021.e06504
Liu, Q., Liu, Z., Li, D., & Gao, Q. (2020). Modeling and forecasting confirmed cases of COVID-19 in China using ARIMA model. Journal of Infection and Public Health, 13(6), 817–822. DOI: https://doi.org/10.1016/j.jiph.2020.04.003
Islam, A. R. M. T., Hasan, M. M., Rahman, M. M., & Rahman, M. A. (2021). Modeling COVID-19 outbreaks in the Middle East using hybrid neural networks. Environmental Science and Pollution Research, 28(25), 31869–31885. DOI: https://doi.org/10.1007/s11356-020-10827-8
Anaraki, A. K., & Shahraki, A. (2021). Forecasting COVID-19 in Iran using hybrid artificial intelligence models. Soft Computing, 25(20), 13071–13087.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. https://www.deeplearningbook.org/
Li, R. et al. (2020). Substantial undocumented infection facilitates the rapid dissemination of novel coronavirus (SARS-CoV-2). Science, 368(6490), 489–493. DOI: https://doi.org/10.1126/science.abb3221
Bandyopadhyay, S. et al. (2021). Forecasting COVID-19 using hybrid models. Pattern Recognition Letters, 145, 1–8. DOI: https://doi.org/10.1016/j.patrec.2020.11.008
Islam, A. R. M. T. et al. (2020). Time series analysis and forecasting of COVID-19 outbreak in Gulf countries. International Journal of Environmental Health Research, 31(6), 682–696. DOI: http://dx.doi.org/10.4018/IJEHMC.20220701.oa3
Adhikari, R., & Agrawal, R. K. (2013). A combination of artificial neural network and ARIMA models for time series forecasting. Neural Computing and Applications, 23(1), 1–11. DOI: http://dx.doi.org/10.1007/s00521-013-1386-y
R Rajkumar, M V Sudhamani, Content based Image Retrieval System using Combination of Color and Shape Features, and Siamese Neural Network. (2019). International Journal of Innovative Technology and Exploring Engineering, 9(2S), 71–77. DOI: https://doi.org/10.35940/ijitee.b1053.1292s19
Magapu, H., Krishna Sai, M. R., & Goteti, B. (2024). Human Deep Neural Networks with Artificial Intelligence and Mathematical Formulas. International Journal of Emerging Science and Engineering, 12(4), 1–2. DOI: https://doi.org/10.35940/ijese.c9803.12040324
Niharika, & Malhotra, S. (2020). Sentiment Analysis using Artificial Neural Network. International Journal of Recent Technology and Engineering (IJRTE), 8(5), 3267–3273. DOI: https://doi.org/10.35940/ijrte.e6450.018520