Forecasting PM10 levels in Sri Lanka: A comparative analysis of machine learning models PM10

Abstract

Forecasting of particulate matter (PM10) which adversely impacts air quality is highly important in ever-urbanizing cities. The relationship between particulate matter and other air quality parameters and climatic parameters is frequently investigated due to their nonlinearity. Machine learning models have been extensively used in these nonlinear predictions and showcased their ability and robustness. However, among the tested machine learning models, a comparative analysis is essential in the localized context to understand the best model that can be used to forecast future scenarios. Therefore, this research investigates the applicability of eight state-of-the-art machine learning models (ANN, Bi-LSTM, Ensemble, XGBoost, CatBoost, LightGBM, LSTM, and GRU) in the prediction of particulate matter in two urbanized areas (Battaramulla and Kandy) Sri Lanka. Regression coefficient, Root Mean Squared Error, Mean Squared Error, Mean Absolute Error, Mean Absolute Relative Error, and Nash-Sutcliffe Efficiency were incorporated to assess the best-suited model for both cities. Results revealed that the Ensemble model has the capability of accurate and precise prediction of PM10 for both cities outperforming all other models (R2≈1). Therefore, the Ensemble model is recommended for future investigation of PM10 for Sri Lanka which has a growing concern due to high air pollution levels.