Urban Air Quality and Health Impact Analysis Based on Machine Learning Models
Abstract
In this paper, an attempt has been made to understand the relations between air quality in urban areas and individuals' health by using the dataset “Urban Air Quality and Health Impact Dataset” enlisted on Kaggle. The dataset comprisess some standard environmental parameters like temperate, humidity, wind speed, and solar exposure along with HealthRelated Risk Scores for top-tier American cities. Predicting Health Risk in Urbanization Using Machine Learning: Applying the linear regression and the random forest models, we attempt to forecast in which ways weather conditions may potentially influence health risks. Based on the results, we note that factors such as temperature and humidity are critical determinants of public health. These models also show a positive relationship between potential environmental variables and the probability of health risks, a measure of value to city planners and health departments. The data could then inform more efficient decisions to address environmental health risks common in cities. In the future, we also intend to overlay real-time data and consider the application of higher-order methods, including deep learning, for improving the precisions of the predictions and facilitating better urban health administration.