Forecasting the Spread and Mortality Trends of COVID-19 in Afghanistan and Iran Using Long Short-Term Memory Neural Networks
A Temporal Data Analysis and Cross-Country Accuracy Comparison
DOI:
https://doi.org/10.61438/sarj.v1i2.145Keywords:
COVID-19, forecasting, mortality, LSTM, epidemiologyAbstract
Objectives: This study aims to investigate and compare the prediction of COVID-19 prevalence and mortality trends in Iran and Afghanistan using the Long Short-Term Memory (LSTM) neural network model.
Methods: Daily epidemiological data from Iran and Afghanistan, spanning 2021 to 2023, were sourced from the Daily World database. The dataset was split into 80% for training and 20% for evaluation. The LSTM model was utilized to predict trends in COVID-19 cases and deaths for both countries.
Results: The LSTM model demonstrated high accuracy in forecasting COVID-19 trends in Afghanistan, achieving R² = 0.98, RMSE = 1.09, and MAE = 0.42. In contrast, the model's performance in Iran was markedly lower, with R² = -0.15, RMSE = 107.64, and MAE = 58.62. The discrepancy may stem from differences in data quality, greater volatility in the Iranian data, and variations in geographical and surveillance systems.
Conclusion: This research highlights the challenges and potential of LSTM models in forecasting COVID-19 trends in developing countries. The results underscore the need for refined approaches that address regional data complexities to enhance the accuracy and utility of predictive tools in health crisis management.
References
[1] World Health Organization. Weekly epidemiological update on COVID-19 - 1 September 2023 [Internet]. Available from: https://www.who.int/publications/m/item/weekly-epidemiological-update-on-covid-19---1-september-2023 [accessed 2024 Dec 19].
[2] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735–80. https://doi.org/10.1162/neco.1997.9.8.1735.
[3] Chimmula VKR, Zhang L. Time series forecasting of COVID-19 transmission in Canada using LSTM networks. Chaos Solitons Fractals. 2020;135:109864. https://doi.org/10.1016/j.chaos.2020.109864.
[4] Shahid F, Zameer A, Muneeb M. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos Solitons Fractals. 2020;140:110212. https://doi.org/10.1016/j.chaos.2020.110212.
[5] Demertzis K, Tsiotas D, Magafas L. Modeling and forecasting the COVID-19 temporal spread in Greece: an exploratory approach based on complex network-defined splines. Int J Environ Res Public Health. 2020;17(13):4693. https://doi.org/10.3390/ijerph17134693.
[6] Pinter G, Felde I, Mosavi A, Ghamisi P, Gloaguen R. COVID-19 pandemic prediction for Hungary: A hybrid machine learning approach. Mathematics. 2020;8(6):890. https://doi.org/10.3390/math8060890.
[7] Wang P, Zheng X, Ai G, Liu D, Zhu B. Time series prediction for the epidemic trends of COVID-19 using the improved LSTM deep learning method: Case studies in Russia, Peru, and Iran. Chaos Solitons Fractals. 2020;140:110214. https://doi.org/10.1016/j.chaos.2020.110214.
[8] Benvenuto D, Giovanetti M, Vassallo L, Angeletti S, Ciccozzi M. Application of the ARIMA model on the COVID-2019 epidemic dataset. Data Brief. 2020;29:105340. https://doi.org/10.1016/j.dib.2020.105340.
[9] Singh V, Poonia RC, Kumar S, Dass P, Agarwal P, Bhatnagar V, et al. Prediction of COVID-19 corona virus pandemic based on time series data using support vector machine. J Discrete Math Sci Cryptogr. 2020;23(5):1583–97. https://doi.org/10.1080/09720529.2020.1784535.
[10] Saba AI, Elsheikh AH. Forecasting the prevalence of COVID-19 outbreak in Egypt using nonlinear autoregressive artificial neural networks. Process Saf Environ Prot. 2020;141:1–8. https://doi.org/10.1016/j.psep.2020.05.029.
[11] Gers FA, Schmidhuber J, Cummins F. Learning to forget: continual prediction with LSTM. Neural Comput. 2000;12(10):2451–71. https://doi.org/10.1162/089976600300015015.
[12] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate [Internet]. 2016. Available from: https://doi.org/10.48550/arXiv.1409.0473.
[13] Graves A, Mohamed A, Hinton G. Speech recognition with deep recurrent neural networks. 2013 IEEE Int Conf Acoust Speech Signal Process. 2013:6645–9. https://doi.org/10.1109/ICASSP.2013.6638947.
[14] Chai T, Draxler RR. Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geosci Model Dev. 2014;7(3):1247–50. https://doi.org/10.5194/gmd-7-1247-2014.
[15] Draper NR, Smith H. Applied regression analysis. 3rd ed. New York: John Wiley & Sons; 1998.
[16] Willmott CJ, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res. 2005;30(1):79–82. https://doi.org/10.3354/cr030079.
[17] Abdollahi J, Irani AJ, Nouri-Moghaddam B. Modeling and forecasting the spread of COVID-19 epidemic in Iran until Sep 22, 2021, based on deep learning [Internet]. 2021. Available from: https://doi.org/10.48550/arXiv.2103.08178.
[18] Makhlouqi F, Goshvarpour A. Predicting COVID-19 incidence and mortality rates in Iran using long short-term memory neural networks. [In Persian].
[19] Karimi Zarchi M, Shishehbari D. Predicting the spread of COVID-19 using time series in Mehriz County. J Iran Health Insur. 2023;6:113–22.
[20] Kafieh R, Arian R, Saeedizadeh N, Amini Z, Serej ND, Minaee S, et al. COVID-19 in Iran: Forecasting pandemic using deep learning. Comput Math Methods Med. 2021;2021:6927985. https://doi.org/10.1155/2021/6927985.
[21] Karimi Zarchi M, Shishehbari D. Modeling cumulative COVID-19 cases in Yazd County using time series techniques and machine learning. Modeling Eng. 2023;21:309–23. https://doi.org/10.22075/jme.2023.29849.2404.
[22] Keller JP, Zhou T, Kaplan A, Anderson GB, Zhou W. Tracking the transmission dynamics of COVID-19 with a time‐varying coefficient state‐space model. Stat Med. 2022;41(13):2745–67. https://doi.org/10.1002/sim.9382.
[23] Timornajad K, Yamagani M. Predicting COVID-19 time series data using LSTM deep learning regression network in Iran. Proceedings of the 5th National Conference on the Application of Modern Technologies in Engineering Sciences. 2021.
[24] Dhake H, Kashyap Y, Kosmopoulos P. Algorithms for hyperparameter tuning of LSTMs for time series forecasting. Remote Sens. 2023;15(8):2076. https://doi.org/10.3390/rs15082076.
[25] Keller JP, Zhou T, Kaplan A, Anderson GB, Zhou W. Tracking the transmission dynamics of COVID‐19 with a time‐varying coefficient state‐space model. Stat Med. 2022;41(13):2745–67. https://doi.org/10.1002/sim.9382.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Salamat Academic & Research Journal
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
