Predicting COVID-19 cases using bidirectional LSTM on multivariate time series

Abstract

To assist policymakers in making adequate decisions to stop the spread of the COVID-19 pandemic, accurate forecasting of the disease propagation is of paramount importance. This paper presents a deep learning approach to forecast the cumulative number of COVID-19 cases using bidirectional Long Short-Term Memory (Bi-LSTM) network applied to multivariate time series. Unlike other forecasting techniques, our proposed approach first groups the countries having similar demographic and socioeconomic aspects and health sector indicators using K-means clustering algorithm. The cumulative case data of the clustered countries enriched with data related to the lockdown measures are fed to the bidirectional LSTM to train the forecasting model. We validate the effectiveness of the proposed approach by studying the disease outbreak in Qatar and the proposed model prediction from December 1st until December 31st, 2020. The quantitative evaluation shows that the proposed technique outperforms state-of-art forecasting approaches.

Keywords: Bi-LSTM; COVID-19; Clustering; Cumulative cases.

Fig. 1

Overview of the proposed prediction approach of daily cumulative cases of COVID-19 using Bi-LSTM on multivariate time series

Fig. 2

Long Short-Term Memory (LSTM) cell

Fig. 3

Unfolded architecture of Bidirectional LSTM

Fig. 4

Cumulative COVID-19 cases in Qatar with lockdown measures

Fig. 5

Distortion score for different numbers of clusters. Elbow corresponds to K = 43

Fig. 6

Cumulative COVID-19 cases of countries having similar demographic and socioeconomic properties

Fig. 7

Forecasting results for Qatar using Bi-LSTM vs. LSTM models trained on Qatar cluster data

Fig. 8

Forecasting results for Qatar using Bi-LSTM with lockdown compared to state-art time series forecasting approaches