The Effects of Weather Conditions on COVID-19 Forecasting, the United Arab Emirates as a Reliable Study Case

Predicting new COVID-19 cases was, and still is, of paramount importance to decision-makers in many countries. Due to its transmission nature, e.g., sneezing, coughing, and physical contact, researchers have developed prediction models that include weather features hoping to improve the forecasting models' predictions. The research did not show any conclusive evidence about the importance of including weather features in forecasting models. Thus, this paper addresses this problem by considering the United Arab Emirates (UAE) COVID-19 cases and weather conditions. Using long-short term memory (LSTM) models, a variant of artificial neural network used for forecasting, we compare a uni-variate, default forecasting model that only considers COVID-19 cases to other bi- and multi-variate models that relies on COVID-19 and weather features. The results show that including weather features in the forecasting models did not significantly improve the accuracy of the default LSTM model;the maximum increase in the coefficient of determination did not exceed 0.02. Moreover, humidity, if considered with other weather features, has a small influence on improving the prediction accuracy. © 2021 IEEE.

What to Forecast When Forecasting New Covid-19 Cases? Jordan and the United Arab Emirates as Case Studies

Covid-19 has exerted tremendous pressure on countries’ resources, especially the health sector. Thus, it was important for governments to predict the number of new covid-19 cases to face this sudden epidemic. Deep learning techniques have shown success in predicting new covid-19 cases. Researchers have used long-short term memory (LSTM) networks that consider the previous covid-19 numbers to predict new ones. In this work, we use LSTM networks to predict new covid-19 cases in Jordan and the United Arab Emirates (UAE) for six months. The populations of both countries are almost the same;however, they had different arrangements to deal with the epidemic. The UAE was a world leader in terms of the number of covid-19 tests per capita. Thus, we try to find if incorporating covid-19 tests in predicting the LSTM networks would improve the prediction accuracy. Building bi-variate LSTM models that consider the number of tests did not improve uni-variate LSTM models that only consider previous covid-19 cases. However, using a uni-variate LSTM model to predict the ratio of covid-19 cases to the number of covid-19 tests have shown superior results in the case of Jordan. This ratio can be used to forecast the number of new covid-19 cases by multiplying this ratio by the number of conducted tests. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.