Artificial neural networks and fuzzy time series forecasting: an application to air quality

Abstract

The arising air pollution has addressed much attention globally due to its detrimental effects on human health and environment. As an early warning system for air quality control and management, it is important to provide precise information about the future concentrations in pollutants. We present here a time series model in predicting the Air Pollution Index (API) from three different stations; industrial, residential, and sub-urban areas between 2000 and 2009. In this paper, the Box-Jenkins approach of seasonal autoregressive integrated moving average (ARIMA), artificial neural network (ANN), and three models of fuzzy time series (FTS) have been compared by using the mean absolute percentage error, mean absolute error, mean square error, and root mean square error. Although all the methods were used as operational tools, the ANN seemed more accurate in forecasting API. The results showed that FTS (i.e. Chen's, Yu's, and Cheng's) performed inconsistent results since the conventional methods of ARIMA outperformed the performance of FTS. However, consistent results were achieved as the ANNs gave the smallest forecasting error compared to FTS and ARIMA.

Development of the method of forecasting the atmospheric air pollution parameters based on error correction by neural-like structures of the model of successive geometric transformations

“…In [13], the authors have developed predictive models of air pollution based on statistics using two neural network architectures: a multilayer perceptron and a nonlinear autoregressive exogenous network. The study [14] deals with the comparison of the seasonal autoregressive integrated moving average, artificial neural network and three models of fuzzy time series using the mean absolute error and the mean square error. It has been found that the accuracy of neural network prediction models is higher than that of other statistical models, but needs to be refined.…”

Deep Random Subspace Learning: A Spatial-Temporal Modeling Approach for Air Quality Prediction

“…Commonly used machine learning algorithms include multiple linear regression (MLR), random forest (RF) [23], support vector regression (SVR) [24], artificial neural networks (ANN) [25], and so forth. Previous studies have found that machine learning methods achieve excellent performance due to the nonlinear relationships within data, meaning that these methods are better suited to parameter statistic models and need less training time than dispersion models [26][27][28]. Deep learning algorithms, as a relative newcomer, have obtained outstanding prediction or detection performances in various application domains such as speech recognition, natural language processing, and computer vision [29].…”

Research on the Topological Properties of Air Quality Index Based on a Complex Network

“…The change of atmospheric composition is attributed to the combustion of fossil fuels [1]. Air pollutants, such as carbon monoxide (CO), respirable particulate matter (PM 2.5 and PM 10 ), nitrogen oxides (NO x ), ozone (O 3 ), sulphur dioxide (SO 2 ), nitrogen dioxide (NO 2 ), and nitric oxide (NO), differ in their reaction properties, chemical composition, time of disintegration, emission, and diffuse ability over short or long distances. Air pollution has both acute and chronic impacts on human health, and causes or aggravates numerous organic and systemic diseases, such as heart disease, respiratory irritation, lung cancer, chronic bronchitis, and acute respiratory infections, which will bring about premature mortality and reduce life expectancy [2][3][4].…”

“…The ARIMA is a traditional forecasting technique, widely used for analyzing nonlinear time series data [8,9]. However, it is constrained by the assumptions of stationarity and linearity, and only suitable for the linear form of time series data [10]. The MLR method is a classical statistical techniques compared to other approaches.…”

“…However, an ANN is unable to present a clear formula for the forecasting model [19][20][21]. Almost as remarkably, many studies successfully and widely employed the hybrid model in pollution index forecasting and proved that the hybrid model generally had more precise forecasts than the monomial forecast model [7,8,10,[22][23][24].The analysis of the AQI time series is difficult because of the irregularity, randomness, and non-stationarity. The existing research methods, such as ARIMA, MLR, ANNs, and hybrid model, are just a forecast of time series data, and cannot capture the pattern information and change law hidden behind AQI fluctuation.…”