Forecasting COVID-19 disease cases using the SARIMA-NNAR hybrid model

Abstract

Background: COVID 19 is a new disease that is associated with high morbidity that has spread around the world. Credible estimating is crucial for control and prevention. Nowadays, hybrid models have become popular, and these models have been widely implemented. Better estimation accuracy may be attained using time-series models. Thus, our aim is to forecast the number of COVID 19 cases with time-series models. Objective: Using time series models to predict deaths due to COVID 19. Design: SARIMA, NNAR, and SARIMA-NNAR hybrid time series models were used using the COVID 19 information of the Republic of Turkey Health Ministry. Participants: We analyzed data on COVID 19 in Turkey from March 11, 2020, to February 22, 2021. Main Measures: Daily numbers of COVID-19 confirmed cases and deaths. Materials and methods: We fitted a seasonal autoregressive integrated moving average (SARIMA) neural network nonlinear autoregressive (NNAR) hybrid model with COVID 19 monthly cases from March 11, 2020, to February 22, 2021, in Turkey. Additionally, a SARIMA model, an NNAR model, and a SARIMA NNAR hybrid model were established for comparison and estimation. Results The RMSE, MAE, and MAPE values of the NNAR model were obtained the lowest in the training set and the validation set. Thus, the NNAR model demonstrates excellent performance whether in fitting or forecasting compared with other models. Conclusions The NNAR model that fits this study is the most suitable for estimating the number of deaths due to COVID 19. Hence, it will facilitate the prevention and control of COVID 19.

Gis Based Spatial Analysis and Prediction of Covid-19 Cases

“…are polynomials in B where B represents the backward shift operator [14] .The seasonal parameters are considered "0" in this case.…”

Comparative analysis of Gated Recurrent Units (GRU), long Short-Term memory (LSTM) cells, autoregressive Integrated moving average (ARIMA), seasonal autoregressive Integrated moving average (SARIMA) for forecasting COVID-19 trends

“… NA NA NA NA NA NA 6 2 NA LSTM, Bidirectional-LSTM, Encoder Decoder-LSTM This study did not provide suggestion on which model performed better and recommended Bayesian inference framework for COVID-19 forecast studies. Demir [30] NA NA NA (2,2) (1,0) (2,1) NA NA NA Neural Network Nonlinear Autoregressive (NNAR)model, SARIMA-NNAR. This study reported that NNAR model as the best model for forecasting COVID-19 in Turkey.…”