Abstract
The effectiveness of predicting the dynamics of the coronavirus pandemic for Russia as a whole and for Moscow is studied for a two-year period beginning March 2020. The comparison includes well-proven population models and statistic methods along with a new data-driven model based on the LSTM neural network. The latter model is trained on a set of Russian regions simultaneously, and predicts the total number of cases on the 14-day forecast horizon. Prediction accuracy is estimated by the mean absolute percent error (MAPE). The results show that all the considered models, both simple and more complex, have similar efficiency. The lowest error achieved is 18% MAPE for Moscow and 8% MAPE for Russia.
Keywords: covid-19 forecasting, time series analysis, total cases prediction, machine learning, SIR
References
- 1.Postnikov E.B. Estimation of covid-19 dynamics “on a back-of-envelope”: Does the simplest sir model provide quantitative parameters and predictions? Chaos, Solitons & Fractals. 2020;135 doi: 10.1016/j.chaos.2020.109841. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 2.Kudryashov N.A., Chmykhov M.A., Vigdorowitsch M. Analytical features of the sir model and their applications to covid-19. Applied Mathematical Modelling. 2021;90:466–473. doi: 10.1016/j.apm.2020.08.057. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3.Perakis G., Singhvi D., Skali Lami O., Thayaparan L. Production and Operations Management; 2022. Covid-19: A multiwave sir-based model for learning waves. [Google Scholar]
- 4.Rahimi I., Gandomi A.H., Asteris P.G., Chen F. Analysis and prediction of covid-19 using sir, seiqr, and machine learning models: Australia, italy, and uk cases. Information. 2021;12(3):109. [Google Scholar]
- 5.Singh P., Gupta A. Generalized sir (gsir) epidemic model: An improved framework for the predictive monitoring of covid-19 pandemic. ISA transactions. 2022;124:31–40. doi: 10.1016/j.isatra.2021.02.016. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 6.Spouge J.L. A comprehensive estimation of country-level basic reproduction numbers r 0 for covid-19: Regime regression can automatically estimate the end of the exponential phase in epidemic data. PloS one. 2021;16(7) doi: 10.1371/journal.pone.0254145. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 7.Kudryashov N.A., Chmykhov M.A., Vigdorowitsch M. AIP Conference Proceedings. Vol. 2425. AIP Publishing LLC; 2022. Comparison of some covid-19 data with solutions of the sir-model. [Google Scholar]
- 8.Abotaleb M., Makarovskikh T. System for forecasting covid-19 cases using time-series and neural networks models. Engineering Proceedings. 2021;5(1):46. [Google Scholar]
- 9.Swapnarekha H., Behera H.S., Nayak J., Naik B., Kumar P.S. Multiplicative holts winter model for trend analysis and forecasting of covid-19 spread in india. SN Computer Science. 2021;2(5):1–15. doi: 10.1007/s42979-021-00808-0. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 10.Awwad F.A., Mohamoud M.A., Abonazel M.R. Estimating covid-19 cases in makkah region of saudi arabia: Space-time arima modeling. PLoS One. 2021;16(4) doi: 10.1371/journal.pone.0250149. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 11.Gambhir E., Jain R., Gupta A., Tomer U. 2020 International conference on smart electronics and communication (ICOSEC) IEEE; 2020. Regression analysis of covid-19 using machine learning algorithms; pp. 65–71. [Google Scholar]
- 12.Zhou B., Yang G., Shi Z., Ma S. Interpretable temporal attention network for covid-19 forecasting. Applied Soft Computing. 2022;120 doi: 10.1016/j.asoc.2022.108691. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 13.Vega R., Flores L., Greiner R. Simlr: Machine learning inside the sir model for covid-19 forecasting. Forecasting. 2022;4(1):72–94. [Google Scholar]
- 14.Bakar M.A., Mohamed N., Pratama D.A., Yusran M.F.A., Aleng N.A., Yanuar Z., Niken L. Modelling lock-down strictness for covid-19 pandemic in asean countries by using hybrid arima-svr and hybrid seir-ann. Arab Journal of Basic and Applied Sciences. 2021;28(1):204–224. [Google Scholar]
- 15.Sboev A., Kudryshov N., Moloshnikov I., Serenko A., Naumov A., Rybka R. Baseline accuracy of forecasting covid-19 cases in moscow region on a year in retrospect using basic statistical and machine learning methods. Journal of Physics: Conference Series. 2021;2036 doi: 10.1016/j.procs.2021.10.028. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 16.Arık S.Ö., Shor J., Sinha R., Yoon J., Ledsam J.R., Le L.T., Dusenberry M.W., Yoder N.C., Popendorf K., Epshteyn A., et al. A prospective evaluation of ai-augmented epidemiology to forecast covid-19 in the usa and japan. NPJ digital medicine. 2021;4(1):1–18. doi: 10.1038/s41746-021-00511-7. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 17.Naumov A., Moloshnikov I., Serenko A., Sboev A., Rybka R. Baseline accuracies of forecasting covid-19 cases in russian regions on a year in retrospect using basic statistical and machine learning methods. Procedia Computer Science. 2021;193:276–284. doi: 10.1016/j.procs.2021.10.028. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 18.Istaiteh O., Owais T., Al-Madi N., Abu-Soud S. 2020 International Conference on Intelligent Data Science Technologies and Applications (IDSTA) IEEE; 2020. Machine learning approaches for covid-19 forecasting; pp. 50–57. [Google Scholar]