Global Air Pollution Prediction using Decision Tree

---

Abstract

Air pollution is a worldwide environmental concern that significantly impacts the health and well-being of individuals across the globe. The impact of air pollutants on the health of human beings, ecosystems, and the climate has spurred significant concern and necessitated comprehensive analysis and understanding. This study provides an in-depth examination of global air pollution trends, sources, and their consequences, drawing from a vast and diverse dataset. The "Global Air Pollution Dataset" serves as the foundation for this analysis, offering a wealth of information that encompasses air quality measurements, emissions data, meteorological variables, and more. The dataset combines historical records with real-time updates, providing a rich resource for researchers, policymakers, and environmental enthusiasts. The proposed model achieved 98% in terms of accuracy using Decision Tree Algorithm to analyze the Pollutants as a public health concern that include particulate matter, carbon monoxide, nitrogen dioxide and ozone.

---

Keywords

Machine Learning, Deep Learning, Decision Tree Algorithm, Random Forest