Association between weather data and COVID-19 pandemic predicting mortality rate: Machine learning approaches

Zohair Malki; El-Sayed Atlam; Aboul Ella Hassanien; Guesh Dagnew; Mostafa A Elhosseini; Ibrahim Gad

doi:10.1016/j.chaos.2020.110137

Association between weather data and COVID-19 pandemic predicting mortality rate: Machine learning approaches

Chaos Solitons Fractals. 2020 Sep:138:110137. doi: 10.1016/j.chaos.2020.110137. Epub 2020 Jul 17.

Authors

Zohair Malki¹, El-Sayed Atlam^{1

2}, Aboul Ella Hassanien³, Guesh Dagnew⁴, Mostafa A Elhosseini^{1

5}, Ibrahim Gad²

Affiliations

¹ College of Computer Science and Engineering, Taibah University, Yanbu, Saudi Arabia.
² Faculty of Science, Tanta University, Egypt.
³ Faculty of Computers and Artificial Intelligence, Cairo University, Egypt.
⁴ Department of Computer Science, Institute of Technology, Dire Dawa University, Ethiopia.
⁵ Mansoura University, Computers Engineering and Control Systems Department, Faculty of Engineering, Mansoura, Egypt.

Abstract

Nowadays, a significant number of infectious diseases such as human coronavirus disease (COVID-19) are threatening the world by spreading at an alarming rate. Some of the literatures pointed out that the pandemic is exhibiting seasonal patterns in its spread, incidence and nature of the distribution. In connection to the spread and distribution of the infection, scientific analysis that answers the questions whether the next summer can save people from COVID-19 is required. Many researchers have been exclusively asked whether high temperature during summer can slow down the spread of the COVID-19 as it has with other seasonal flues. Since there are a lot of questions that are unanswered right now, and many mysteries aspects about the COVID-19 that is still unknown to us, in-depth study and analysis of associated weather features are required. Moreover, understanding the nature of COVID-19 and forecasting the spread of COVID-19 request more investigation of the real effect of weather variables on the transmission of the COVID-19 among people. In this work, various regressor machine learning models are proposed to extract the relationship between different factors and the spreading rate of COVID-19. The machine learning algorithms employed in this work estimate the impact of weather variables such as temperature and humidity on the transmission of COVID-19 by extracting the relationship between the number of confirmed cases and the weather variables on certain regions. To validate the proposed method, we have collected the required datasets related to weather and census features and necessary prepossessing is carried out. From the experimental results, it is shown that the weather variables are more relevant in predicting the mortality rate when compared to the other census variables such as population, age, and urbanization. Thus, from this result, we can conclude that temperature and humidity are important features for predicting COVID-19 mortality rate. Moreover, it is indicated that the higher the value of temperature the lower number of infection cases.

Keywords: COVID-19; Humidity; Machine learning; OLS; Prediction; Temperature.