Risk Assessment of Global Temperature Anomalies Using Intelligence Frameworks: Evaluating the Impact of Socioeconomic Factors and with a Case Study on Heatstroke Deaths in India

Rising global temperatures due to climate change have significantly increased the risk of heat-related illnesses, particularly heatstroke, in various regions. As global warming continues, it is crucial to understand patterns in heatstroke occurrences to predict and address future impacts. This study uses Machine Learning (ML) techniques to explore the connection between increasing temperatures and heatstroke incidents. ML models analyze extensive datasets containing meteorological data, health records, and geographical variables to uncover correlations between temperature spikes and heatstroke prevalence. The research incorporates supervised learning models such as linear Regression, lasso regression, ridge regression and voting regressor to predict high-risk periods and regions vulnerable to heatstroke. Additionally, time-series analysis and Prophet model is used to forecast future heatstroke cases by identifying climate data trends. These models are trained and validated using historical temperature and heatstroke fatality data from different regions. Preliminary findings indicate that extreme heatwaves, along with humidity and urbanization factors, significantly contribute to heatstroke occurrences. This study, leveraging ML, aims to improve the ability to predict and prevent heat-related health crises, offering valuable insights for public health planning, early-warning systems, and climate adaptation strategies to protect populations from the adverse effects of global warming.