Prediction of Air Quality Index of Trivandrum City using Machine Learning Methods

Air Pollution is a global problem that has affected mankind for a very long time. It causes lasting damage to human health and property. As such, governments around the world adopted a system of measuring air pollutant concentrations called Air Quality Index, which provides an easier way to keep track of pollutant concentrations. In this study, we employed two machine learning models, the Extreme Learning Machine model is a variant of the traditional Single Layer Feed forward Artificial Neural Network, which prioritizes speed over accuracy when it comes to making predictions. The Seemingly Unrelated Regression is a traditional statistical model which finds relationships between variables that are uncorrelated with each other but whose error terms correlate, hence the term ?seemingly unrelated?. The models were trained using three years of data from 2018 - 2020. The optimum combinations of input variables to be used to maximize accuracy were also discovered during this training period. They are then tested for the first three months of 2021. The scoring was evaluated using R2 scoring method and we observed that the ELM model scored much higher accuracies than the SUR model, making it best suited for predicting the air quality of Trivandrum City.