Empirical analysis of impact of weather and air pollution parameters on COVID-19 spread and control in India using Machine Learning Algorithm

Abstract

The COVID-19 has affected and threatened the world health system very critically throughout the globe. In order to take preventive actions by the agencies in dealing with such a pandemic situation, it becomes very necessary to develop a system to analyze the impact of environmental parameters on the spread of this virus. Machine learning algorithms and artificial Intelligence may play an important role in the detection and analysis of the spread of COVID-19. This paper proposed a twinned gradient boosting machine (GBM) to analyze the impact of environmental parameters on the spread, recovery, and mortality rate of this virus in India. The proposed paper exploited the four weather parameters (temperature, humidity, atmospheric pressure, and wind speed) and two air pollution parameters (PM2.5 and PM10) as input to predict the infection, recovery, and mortality rate of its spread. The algorithm of the GBM model has been optimized in its four distributions for best performance by tuning its parameters. The performance of the GBM is reported as excellent (where R2 = 0.99) in training for the combined dataset comprises all three outcomes i.e. infection, recovery and mortality rates. The proposed approach achieved the best prediction results for the state, which is worst affected and highest variation in the atmospheric factors and air pollution level.

Navigating the future: machine learning's role in revolutionizing antimicrobial stewardship and infection prevention and control

“…Several ML models have used clinical data to develop hepatitis B virus (HBV) risk assessment models but remain in the preclinical deployment phase [22]. From using weather and air pollution as inputs to models that predict infection, recovery, and mortality rates for COVID-19 [23], to integrating multiple modeling techniques to enhance understanding of Mpox spread [24], ML techniques have the potential to inform policy making.…”