Key points are not available for this paper at this time.
Introduction: Traditional statistical methods cannot find quantitative relationship from environmental data. Methods: We selected gene expression programming (GEP) to study the relationship between pollutant gas and PM 2.5 (PM 10 ). They were used to construct the relationship between pollutant gas and PM 2.5 (PM 10 ) with environmental monitoring data of Xi’an, China. GEP could construct a formula to express the relationship between pollutant gas and PM 2.5 (PM 10 ), which is more explainable. Back Propagation neural networks (BPNN) was used as the baseline method. Relevant data from January 1st 2021 to April 26th 2021 were used to train and validate the performance of the models from GEP and BPNN. Results: After the models of GEP and BPNN constructed, coefficient of determination and RMSE (Root Mean Squared Error) are used to evaluate the fitting degree and measure the effect power of pollutant gas on PM 2.5 (PM 10 ). GEP achieved RMSE of 8.7365–14.6438 for PM 2.5 ; RMSE of 13.2739–45.8769 for PM 10 , and BP neural networks achieved average RMSE of 13.8741–34.7682 for PM 2.5 ; RMSE of 29.7327–52.8653 for PM 10 . Additionally, experimental results show that the influence power of pollutant gas on PM 2.5 (PM 10 ) situates between −0.0704 and 0.6359 (between −0.3231 and 0.2242), and the formulas are obtained with GEP so that further analysis become possible. Then linear regression was employed to study which pollutant gas is more relevant to PM 2.5 (PM 10 ), the result demonstrates CO (SO 2 , NO 2 ) are more related to PM 2.5 (PM 10 ). Discussion: The formulas produced by GEP can also provide a direct relationship between pollutant gas and PM 2.5 (PM 10 ). Besides, GEP could model the trend of PM 2.5 and PM 10 (increase and decrease). All results show that GEP can be applied smoothly in environmental modelling.
Wang et al. (Tue,) studied this question.