2024 11th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN)

Abstract

The study delves into the realm of air quality forecasting, employing the LASSO (Least Absolute Shrinkage and Selection Operator) modeling technique for enhanced predictive accuracy. Utilizing a diverse dataset encompassing meteorological parameters, pollutant concentrations, and other relevant factors, the research explores the robustness of LASSO regression in predicting air pollution dynamics. The analysis establishes correlations and identifies key predictors, shedding light on the intricate relationships within the data. The paper contributes valuable insights to the field of air quality prediction, showcasing the efficacy of LASSO modeling in providing accurate and reliable forecasts, thus facilitating proactive measures for pollution mitigation and environmental management. Additionally, the aim of the paper is to investigate whether the COVID-19 pandemic exerted any discernible impact on pollution levels.