Impact of Atmospheric Features for COVID-19 Prediction

Abstract

In the context of contagious diseases, recent advances in experimental techniques have not only generated a dramatic increase in the amount and diversity of data but also an ever increasing and complexifying molecular biology with context to meteorological parameters. To combat this probable inefficiency, decision tree-based methods have emerged to be one of the finest data ensembles showcasing excellent accuracy in combining interpretability. For past infectious diseases like influenza and severe acute respiratory syndrome (SARS), etc., direct correlations were spotted with respect to meteorological parameters including temperature, humidity and air pollution among others. The present study targets to explore the association between COVID-19 mortality rates and weather parameters for which the daily death numbers of corona virus disease 2019, meteorological parameters and air pollution data from March 28, 2020 to April 22, 2020 of different states of India were collected. To explore the effect of the minimum temperature, maximum temperature, minimum humidity and maximum humidity on the infection count of COVID-19, the gradient boosting model (GBM) has been implemented thereby achieving optimal performance by tuning its parameters. For prediction of active cases in Maharashtra, the GBM results stand at its best accuracy of R² as 0.95. For the prediction of recovered cases of COVID-19 in Rajasthan and Kerala, R² equals 0.98. The present study explores the correlation between atmospheric parameters and transmission rate of COVID-19 in different states of India thereby predicting the active and recovered cases of COVID-19 and establishing an efficient tree-based machine learning approach to explore the effect of temperature and humidity on the transmission rate of the said disease.