Air Quality Prediction Using Machine Learning Models: A Predictive Study in the Himalayan City of Rishikesh

Air quality is a critical aspect of urban environmental health that impacts human well-being and ecosystem. Improving air quality by reducing AQI (Air Quality Index) levels directly contributes to achieving sustainable development goals (SDGs), mainly SDG 3 (good health and well-being) and SDG 11 (sustainable cities and communities). Rishikesh, nestled in the Himalayan foothills, faces unique challenges of deteriorating air quality due to its geographical and climatic conditions. This work presents machine learning (ML) approach for forecasting the Air Quality Index (AQI) of Rishikesh City. This study leverages data collected from the city over the past years, encompassing parameters such as carbon monoxide (CO), particulate matter (PM2.5 and PM10), nitrogen dioxide (NO2), ozone (O3) and sulfur dioxide (SO2), and models like the extreme gradient boosting regressor, extra-tree regressor, gradient boosting regressor, and random forest regressor were utilized for the purpose of prediction. Various performance metrics were used to evaluate the prediction accuracy of the applied models. The results show how these methods effectively predict Rishikesh's AQI levels, which allows for the early implementation of preventative actions to decrease air pollution and shield public health. This research aids the development of air quality forecasting methodologies. It helps urban planners and legislators create workable plans for smaller communities where air quality is declining and has not got much attention.