Abstract
The air quality index (AQI) indicates the short-term air quality situation and changing trend of the city, which includes six air pollutants: PM2.5, PM10, CO, NO2, SO2 and O3. Due to the diversity of pollutants and the fluctuation of single pollutant time series, it is a challenging task to find out the main pollutants and establish an accurate forecasting system in a city. Previous studies primarily focused on enhancing either forecasting accuracy or stability and failed to analyze different air pollutants at length, leading to unsatisfactory results. In this study, a model selection forecasting system is proposed that consists of data mining, data analysis, model selection, and multi-objective optimized modules and effectively solves the problems of air pollutants monitoring. The proposed system employed fuzzy C-means cluster algorithm to analyze 13 original AQI series, and fuzzy comprehensive evaluation is used to find out the main air pollutants in each city. And then multiple artificial neural networks are used to forecast the main air pollutants for each category and find the optimal models. Finally, the modified multi-objective optimization algorithm is used to optimize the parameters of optimal models and model selection to obtain final forecasting values from optimal hybrid models. The experiment results of datasets from 13 cities in the Beijing–Tianjin–Hebei Urban Agglomeration demonstrated that the proposed system can simultaneously obtain efficient and reliable data for air quality monitoring.
Highlights
In recent years, air pollution has received increasing attention due to the negative effects, such as respiratory diseases, that it has on human health (Jiang et al, 2017)
The evaluation part involves feature extraction and finding out the main air pollutants; in the forecasting part, a new metric is developed to find the optimal model in each category, and optimal forecasting models are optimized with modified gray wolf optimization (DEGWO) optimization algorithm and leave-one-out deciding weight strategy to improve the accuracy of forecasting results and provide support for early warning systems
Rand(0, 1) represents a random number in [0, 1]. p 1, 2/, d. k 1, 2/, psize Initialize crossover probability Pc and scaling factor F; Initialize a, A, and C; Evaluate f for all individuals in the parent population; Sort the parent population in a non-decreasing order, according to the objective function value; Xα is the best individual in the parent population of gray wolves; Xβ is the second individual in the parent population of gray wolves; Xδ is the third individual in the parent population of gray wolves; While (t < MaxGen) for each individual in the parent population of gray wolves Update the position using the following equation; FIGURE 1 | Flowchart of air quality index forecasting system for Beijing–Tianjin–Hebei Urban Agglomeration
Summary
Air pollution has received increasing attention due to the negative effects, such as respiratory diseases, that it has on human health (Jiang et al, 2017). The evaluation part involves feature extraction and finding out the main air pollutants; in the forecasting part, a new metric is developed to find the optimal model in each category, and optimal forecasting models are optimized with modified gray wolf optimization (DEGWO) optimization algorithm and leave-one-out deciding weight strategy to improve the accuracy of forecasting results and provide support for early warning systems. We use long short-term memory (LSTM), backpropagation neural network (BPNN), adaptive network-based fuzzy inference system (ANFIS), generalized regression neural network (GRNN), and SVM models to forecast the main air pollutants time series, and a developed new metric is used to select optimal forecasting model All these individual forecasting models’ predictors based on the leave-one-out deciding weight strategy are optimized by the DEGWO optimization algorithm, and the final forecasting results are obtained. In the forecasting process, an improved multiobjective optimization algorithm is used to optimize the parameters of the single forecasting model, which improves the prediction accuracy and improves the stability of the single model 4) The model selection index is used to select the optimal forecasting value from the optimal hybrid model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
