AI Big Data System to Predict Air Quality for Environmental Toxicology Monitoring

Abstract

Pollutants in the air have a detrimental effect on both human existence and the environment. Because it is closely linked to climate change and the effects of global warming, research on air quality is currently receiving attention from a variety of disciplines. The science of forecasting air quality has evolved over time, and the actions of different gases (hazardous elements) and other components directly affect the health of the ecosystem. This study aims to present the development of a prediction system based on artificial intelligence models using a database of air quality sensors.This study develops a prediction model using machine learning (ML) and a Decision Tree (DT) algorithm that can enable decision harmonization across different industries with high accuracy. Based on pollutant levels and the classification outcomes from each cluster's analysis, statistical forecasting findings with a model accuracy of 0.95 have been achieved. This may act as a guiding factor in the development of air quality policies that address global consequences, international rescue efforts, and the preservation of the gap in air quality index standardization.