Applying Machine Learning for Predictive Analysis for Air Quality Assessment across different Districts in Uttarakhand

Air quality prediction has generally been motivated by public health concerns, however the impact of climate change on air quality has rendered old methodologies unreliable. Factors such as emission sources and ambient factors are no longer adequate to assess air quality. Manual predictions have been ineffectual, highlighting the necessity for accurate air quality prediction tools. Machine learning has emerged as an important tool for this goal, taking into account a variety of characteristics such as pollutant levels, geographic location, and weather conditions. Reliable projections require accurate predictions of air quality based on these variables. This research analyses multiclass air quality prediction models that use machine learning approaches. We used XGBoost and Random Forest classifiers in our analysis. While both models have good accuracy, the results of this study show that the Random Forest and XGBoost models have relatively high accuracy rates when predicting air quality from the dataset. The Random Forest model slightly beats the XGBoost model, achieving an accuracy of 96% versus 95%.