With the increasing irreversible damage caused by air pollution, an early warning system to send warning information to human beings so that they can avoid more harm caused by air pollution is required. A reliable warning system can provide valuable information to protect mankind from the effects of pollution and can act as a tool that allows regulators to implement corresponding measures to reduce air pollution. However, the previous most valuable research studies were focused on pollution forecasting and the extent to which pollution affects health, and the aim of only a few studies was to analyze pollution from an application perspective and to construct a reasonable early warning system. In this study, an air pollution early warning system was constructed, which comprises two modules: an air pollution forecasting module and an air quality evaluation module. In the forecasting module, two denoising methods and a multi-objective optimization algorithm are integrated into a novel hybrid forecasting model. In the evaluation module, fuzzy synthetic evaluation is used to evaluate air quality objectively. To verify the performance of the proposed early warning system, hourly pollutants concentration data were used in a case study of three metropolises in China and three numeric simulation experiments were conducted. The simulation results show that the forecasting performance of the L2,1RF-ELM model used in this study is better than the traditional neural network, and the forecasting model proposed in this paper is better than the traditional statistical model ARIMA. Moreover,the early warning system performed well in terms of highly accurate forecasting and accurate evaluation in the three research areas.

Introduction

For nearly a century, the rapid development of industrialization and urbanization has increased the amount of energy consumed by human activities and caused serious air pollution in the world. Scholars have conducted a significant number of air pollution research studies. The results of extensive studies indicate that exposure to air pollution can cause a variety of diseases (Cohen et al., 2017; Guo et al., 2016). Moreover, air pollution can also be detrimental to the ecosystem, leading to the greenhouse effect, ozone layer destruction, acid rain, reduced solar radiation, etc. (Anwar et al., 2016; Desonie, 2007; Ramanathan and Feng, 2009). Therefore, accurate and authentic air quality information is increasingly needed to enable industries to minimize their production of pollutants and residents to adjust their activities promptly to mitigate the damage caused by major pollution. To diminish the effects of air pollution, scholars have focused on analyzing and forecasting the concentrations of pollutants, devoting their efforts to providing highly accurate forecasting. During the past one hundred years, many forecasting methods were proposed, the most popular of which can be classified into three categories: physical, statistical, and artificial intelligence models (Bai et al., 2018). Physical models use the physicochemical process of pollutants in the atmosphere as the entry point for forecasting pollutant concentrations. Statistical methods can be divided into causal models and time series models according to their fundamental characteristics. The assumption of causal models is that the historical relationship between dependent and independent variables will remain valid in the future.