FORECASTING OF COVID-۱۹ WITH USING SARIMA MODEL IN YAZD, MAYBOD AND ARDAKAN CITIES

Coronavirus disease ۲۰۱۹ is a respiratory disease caused by acute respiratory syndrome coronavirus-۲. Forecasting the number of new cases and deaths during todays can be a useful step in predicting the costs and facilities needed in the future. This study aims to modeling and predict new cases and deaths efficiently in the future. In this article, the seasonal autoregressive integrated moving average (SARIMA) model was tested to predict the trend of the Covid-۱۹ disease in the cities of Yazd, Meybod and Ardakan. Several SARIMA models with different parameters were fitted on the data and compared using the root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) evaluation criteria. According to the obtained results, the best model for cumulative cases hospitalization in Yazd, Ardakan, and Meybod is SARIMA(۱,۲,۲)(۲,۰,۱), SARIMA(۳,۲,۳)(۱,۰,۰), and SARIMA(۳,۲,۲)(۱,۰,۱), and for the cumulative cases of deaths in Yazd, Ardakan and Meybod, respectively, SARIMA(۱,۱,۳)(۱,۰,۱), SARIMA(۲,۲,۳)(۲,۰,۱) and SARIMA(۴,۲,۳) (۲,۰,۳), were chosen as the best model. The results of the analysis showed that the SARIMA model is suitable for predicting the spread of Covid-۱۹ in the near future. and can provide a proper understanding of the process of the spread of the Covid-۱۹ disease in these areas so that by taking precautionary measures and formulating appropriate policies, this epidemic can be overcome effectively.

کلیدواژه ها:

Covid-۱۹ ، forecasting ، time series ، Statistical modeling ، SARIMA.