Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation

Abstract

h i g h l i g h t sWe propose a novel hybrid model to forecast PM 2.5 pollution.Using trajectory based geographic parameter as an extra input to ANN model. Applying prediction strategy at different scales and then sum them up. The model is capable to predict the high peaks of PM 2.5 concentrations. a b s t r a c tIn the paper a novel hybrid model combining air mass trajectory analysis and wavelet transformation to improve the artificial neural network (ANN) forecast accuracy of daily average concentrations of PM 2.5 two days in advance is presented. The model was developed from 13 different air pollution monitoring stations in Beijing, Tianjin, and Hebei province (Jing-Jin-Ji area). The air mass trajectory was used to recognize distinct corridors for transport of "dirty" air and "clean" air to selected stations. With each corridor, a triangular station net was constructed based on air mass trajectories and the distances between neighboring sites. Wind speed and direction were also considered as parameters in calculating this trajectory based air pollution indicator value. Moreover, the original time series of PM 2.5 concentration was decomposed by wavelet transformation into a few sub-series with lower variability. The prediction strategy applied to each of them and then summed up the individual prediction results. Daily meteorological forecast variables as well as the respective pollutant predictors were used as input to a multi-layer perceptron (MLP) type of back-propagation neural network. The experimental verification of the proposed model was conducted over a period of more than one year (between September 2013 and October 2014). It is found that the trajectory based geographic model and wavelet transformation can be effective tools to improve the PM 2.5 forecasting accuracy. The root mean squared error (RMSE) of the hybrid model can be reduced, on the average, by up to 40 percent. Particularly, the high PM 2.5 days are almost anticipated by using wavelet decomposition and the detection rate (DR) for a given alert threshold of hybrid model can reach 90% on average. This approach shows the potential to be applied in other countries' air quality forecasting systems.

Predicting PM2.5 Concentrations Using Artificial Neural Networks and Markov Chain, a Case Study Karaj City

“…However, the R 2 in our study for MLP and RBF was 0.92 and 0.93, respectively. We compared the results our MLP neural network with the results of Voukantsis et al (2011) andFeng et al (2015) and found that our model presented a suit able performance in predicting PM 2.5 concentrations in Karaj City. Feng et al (2015) obtained RMSE rate between 28 to 36 for one day and two days PM 2.5 pre diction using an MLP neural network.…”

“…Also, we applied the Nash Sutcliffe Efficiency Coefficient (E), coefficient of determination (R 2 ) and the Index of Agreement (IA), between the observed and predicted data to illustrate the validity of the model (Feng et al, 2015;Voukantsis et al, 2011;Krause et al, 2005). (7) (8) (9) (10) (11) Where P and M are the predicted and the observed values of PM 2.5 at the time t, respectively, and -M and -P are the average of predicted and observed values, respectively and n is the number of data.…”

Spatial and Temporal Characteristics and Main Contributing Regions of High PM2.5 Pollution in Hong Kong

“…The analysis of the air masses provided insights into the source regions that contributed to Hong Kong's PM 2.5 pollution (Feng et al, 2015). The 48-h backward trajectories of air masses arriving in Hong Kong (22.2°N, 114.1°E) at a height of 100 m above the ground were generated for every 2-h interval on episode days, a total of 216 backward trajectories were generated, with December 23 omitted from analysis because of data unavailability (Fig.…”

A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN

“…These models attempt to find patterns directly from the input data, rather than numerical simulations. Some of the widely used models are linear regression, Geographically Weighted Regression (Ma et al, 2014), Land Use Regression (Eeftens et al, 2012), Support Vector Machine (Osowski et al, 2007) and Artificial Neural Networks (Voukantsis et al, 2011, Feng et al, 2015. Various attempts have also been made to combine different methods in order to achieve better performance (Sanchez et al, 2013;Adams & Kanaroglou, 2016).…”