Multi-Horizon Forecasting of Average Daily $\text{PM}_{2.5}$ Concentration: A Case Study of Air Pollution in Singapore

Understanding the spatial and temporal dynamics of surface concentrations of particulate matter ($\mathbf{PM}_{2.5}$ and PM10) is essential in air quality modelling and climate research. Forecasting of air pollutants is necessary to understand the variation of pollutants and to plan and implement air pollution control measures. This work proposes a methodology for forecasting $\mathbf{PM}_{2.5}$ concentration using various meteorological parameters over multiple time horizons. The proposed deep learning-based models forecast the daily average values concentration for $\mathbf{PM}_{2.5}$ in Singapore. The performance metrics indicate the efficacy of the proposed model in forecasting $\mathbf{PM}_{2.5}$ concentrations over different horizons. The analysis shows that $\mathbf{PM}_{2.5}$ concentrations are best forecasted for the 3-days ahead scenario, with RMSE and MAPE being 3.767 $\mu \mathrm{g}/\mathrm{m}3$ and 6.82%, respectively.

I. Introduction

Air quality refers to air contamination by various pollutants like dust, smoke, smog, and air impurities. The leading cause of air pollutants and poor air quality are anthropogenic activities, soaring urbanization, and thriving industrialization. Air pollution is among the top five global mortality risk factors [1]. In 2012, World Health Organisation allocated one out of nine deaths to air pollution [2], among them, three million deaths are only due to outdoor air pollution. Pollution due to Particulate Matter (PM) is considered the third ultimate reason of death for 2017 in India, including 56% because of vulnerability to the outdoor accumulation and 44% allocated for domiciliary air pollution [3]. Urban areas like Delhi, Kolkata, and Mumbai, with a population exceeding 46 million, face seriously deteriorated air quality due to massive-scale expansion in anthropogenic activities and population density [4]. The long-term effects of air pollution are hazardous diseases like chronic asthma, cardiovascular diseases, pulmonary insufficiency, cardiovascular mortality, and perinatal disorders, leading to infant mortality in adult age [5]. A similar problem persists in urbanized areas, which need immediate attention and better prediction to reduce the burden of diseases and improve the quality of life of their residents. The need to regulate air quality is vital in places with high urbanization and smaller area, e.g., Singapore, for a better health perspective of the residents and visitors.