Modified Extreme Gradient Boosting Algorithm for Prediction of Air Pollutants in Various Peak Hours

Machine learning is a fascinating field that involves teaching machines to learn patterns and make predictions or decisions without being explicitly programmed to do so. Machine learning continues to advance rapidly, with ongoing research and development pushing the boundaries of what is possible. It is a crucial technology in the era of big data, providing powerful tools for extracting insights and making predictions from large and complex datasets. Air pollution is a combination of dangerous substances that can be both generated by humans and naturally produced. The major sources of pollution cause by people are motor vehicle emissions, petroleum products and normal gas used to heat home, waste from industry and power plants, especially coal-fired ones and smells from chemicals. This study demonstrates how urban centers’ morning and evening rush hours are related to air pollution from transportation. The main goal of this research is to comprehend how the pollutants PM2.5, PM10, SO2, and NO2 vary throughout different peak hours. The pollution data set was collected and evaluated from the suburbs of Chennai, including Alandur, Arumbakkam, Kodungaiyur, Manali, and Velachery. This paper proposed novel technique called Modified Extreme Gradient Boosting Algorithm (MXGBA) to forecast fluctuations in PM2.5, PM10, SO2, and NO2 levels during peak hours. The algorithm’s performance was compared to that of the Extreme Gradient Boosting (XGBA) and the Modified Extreme Gradient Boost Algorithm (MXGBA) demonstrated improved prediction accuracy and reduced error rate.