Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jun;8(6):e09578.
doi: 10.1016/j.heliyon.2022.e09578. Epub 2022 Jun 2.

Forecasting COVID19 parameters using time-series: KSA, USA, Spain, and Brazil comparative case study

Souad Larabi-Marie-Sainte  1 , Sawsan Alhalawani  1 , Sara Shaheen  1 , Khaled Mohamad Almustafa  2 , Tanzila Saba  3 , Fatima Nayer Khan  2 , Amjad Rehman  3
Affiliations

Forecasting COVID19 parameters using time-series: KSA, USA, Spain, and Brazil comparative case study

Souad Larabi-Marie-Sainte et al. Heliyon. 2022 Jun.

Abstract

Many countries are suffering from the COVID19 pandemic. The number of confirmed cases, recovered, and deaths are of concern to the countries having a high number of infected patients. Forecasting these parameters is a crucial way to control the spread of the disease and struggle with the pandemic. This study aimed at forecasting the number of cases and deaths in KSA using time-series and well-known statistical forecasting techniques including Exponential Smoothing and Linear Regression. The study is extended to forecast the number of cases in the main countries such that the US, Spain, and Brazil (having a large number of contamination) to validate the proposed models (Drift, SES, Holt, and ETS). The forecast results were validated using four evaluation measures. The results showed that the proposed ETS (resp. Drift) model is efficient to forecast the number of cases (resp. deaths). The comparison study, using the number of cases in KSA, showed that ETS (with RMSE reaching 18.44) outperforms the state-of-the art studies (with RMSE equal to 107.54). The proposed forecasting model can be used as a benchmark to tackle this pandemic in any country.

Keywords: COVID-19; Drift; Exponential smoothing; Forecasting; Holt; Linear regression; Time-series.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The overall methodology pipeline.
Figure 2
Figure 2
KSA: the time-series representing the number of cases (from March 2 to May 30). The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 3
Figure 3
KSA: the differenced time-series for the number of cases (from March 2 to May 30). The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 4
Figure 4
KSA – Parameter setting for SES using the number of cases. The Y-axis represents the RMSE values and the X-axis stands for the different values of alpha.
Figure 5
Figure 5
KSA – Parameter setting for Holt using the number of cases. The Y-axis represents the RMSE values (in both panels (a) and (b)) and the X-axis stands for the values of alphaH (in panel (a)) and beta (in panel (b)).
Figure 6
Figure 6
KSA Dataset – Residuals test for ETS forecasting model (from March 2 to May 30). The Y-axis represents the residuals values (in panel (a)), the ACF values (in panel (b)), and number count (in panel (c)). While the X-axis indicates the number of days (in panel (a)), the lags (in panel (b)), and the residuals (in panel (c)).
Figure 7
Figure 7
KSA – Boxplot of the Number of COVID19 cases forecasted using the ETS method between May 30 – June 9. The Y-axis represents the number of cases and the X-axis stands for the date.
Figure 8
Figure 8
KSA - Number of COVID19 casthe es forecasted using ETS method between May 30 – June 30 (P-Value <0.05). The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 9
Figure 9
Brazil - The time-series representing number of cases (from Feb 26 to May 21). The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 10
Figure 10
Brazil - COVID19 forecasted number of cases from May 22–31. The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 11
Figure 11
Brazil - COVID19 forecasted number of cases for June 20204.3 Forecasting the number of cases in the US. The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 12
Figure 12
US - Number of COVID19 cases forecasted (testing set May 22–31) using all the methods. The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 13
Figure 13
US – Boxplots of the real and the forecasted values of number of cases (May 22–31,2020). The Y-axis represents the number of cases and the X-axis indicates the forecasting methods used and real values.
Figure 14
Figure 14
US – the Number of COVID19 cases forecasted (until June 30,2020) using ETS method. The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 15
Figure 15
Spain - Number of COVID19 cases forecasted (until June 30,2020) using ETS and Holt methods. The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
Figure 16
Figure 16
KSA - Representation of the Multiple Regression Model. The Y-axis represents the number of deaths and the X-axis stands for the time (the number of days).
Figure 17
Figure 17
KSA – The residuals from the MLR model. The Y-axis represents the residuals values (in panel (a)), the ACF values (in panel (b)), and number count (in panel (c)). While the X-axis indicates the number of days (in (a)), the lags (in (b)), and the residuals (in (c)).
Figure 18
Figure 18
Scatter plot of the residuals (represented in the Y-axis in both panels (a) and (b)) against “Cases” variable (indicated in the X-axis in panel (a)) and the fitted model (indicated in the X-Axis in panel (b)).
Figure 19
Figure 19
KSA Death – Number of COVID19 deaths forecasted (until June 30) using Drift model. The Y-axis represents the number of cases and the X-axis stands for the time (the number of days).
See this image and copyright information in PMC

References

    1. Alzahrani S.I., Aljamaan I.A., Al-fakih E.A. Forecasting the spread of the COVID-19 pandemic in Saudi Arabia using ARIMA prediction model under current public health interventions. J. Infect. Public Health. 2020;13(7):914–919. - PMC - PubMed
    1. Alboaneen D., Pranggono B., Alshammari D., Alqahtani N. Predicting the epidemiological outbreak of the coronavirus disease 2019 (COVID-19) in Saudi Arabia. Int. J. Environ. Res. Publ. Health. 2020;17(12):4568. - PMC - PubMed
    1. Tian C.W., Wang H., Luo X.M. Time-series modelling and forecasting of hand, foot and mouth disease cases in China from 2008 to 2018. Epidemiol. Infect. J. 2019;147(82):1–3. - PMC - PubMed
    1. Maleki M., Mahmoudi M.R., Wraith D., Pho K.H. Time series modelling to forecast the confirmed and recovered cases of covid-19. Travel Med. Infect. Dis. J. 2020;37:101–742. - PubMed
    1. Papas tefanopoulos V., Linardatos nd P., Kotsiantis S. COVID-19 : a comparison of time series methods to forecast percentage of active cases per population. Appl. Sci. 2020;10(11):1–15.

LinkOut - more resources