“…Traditional statistical models such as partial least squares regression model ( Polat and Gunay, 2015 ), generalized Markov model ( Sun et al., 2013 ; Alyousifi et al., 2019 ), Bayesian method ( Riccio et al., 2006 ; Liu et al., 2008 ; Faganeli Pucer et al., 2018 ), etc., are often used for the prediction of air pollutant concentration on time series. However, because these models all have the shortcoming of over-simplified, they inherently have difficulties in unraveling the nonlinear interaction relationship between multivariate factors and PM 2.5 concentration, so that the favorable factors for PM 2.5 prediction cannot be fully utilized ( Ni et al., 2017 ).…”