An innovative hybrid air pollution early-warning system based on pollutants forecasting and Extenics evaluation

Abstract Air pollution poses a substantial threat to society and is considered one of the greatest environmental hazards for human beings. It is of great importance to develop air pollution early warning systems to alleviate the urgency and necessity of air quality monitoring and analysis. However, current early warning systems rarely focus on mining of pollutant characteristics and their corresponding scientific evaluation. In this study, we investigate an innovative hybrid air quality early warning system that comprises characteristics estimation, prediction, and evaluation. First, four different distribution functions with two estimation methods were applied for quarrying the characteristics of pollutants; Afterward, a hybrid forecasting model was proposed combined with an advanced data processing technique—a neural network and a new heuristic algorithm. For further mining the features of pollutants, two interval approaches as well as Extenics evaluation were utilized as indispensable components of the developed system. Simulation of pollutants series, including PM 2.5 , SO2, NO2, CO, and O3 are in line with lognormal distribution using certain parameters, and forecasting results are in good accordance with the empirical data using multiple criterion systems, i.e., MAE, MSE, RMSE, MAPE, MdAPE, FB, DA, and R 2 for deterministic forecasting and with IFCP and IFNAW for interval forecasting. Eight deterministic forecasting criterion for pollutants forecasting measurement indicate that the developed early warning system can achieve good performance in terms of its accuracy and effectiveness. Additionally, the positive interval forecasting results and good precision of Extenics evaluation indicate the efficiency and scalability of the designed early warning system.