Using Seven Types of GM (1, 1) Model to Forecast Hourly Particulate Matter Concentration in Banciao City of Taiwan

• Published in: Water, air, and soil pollution Vol. 217; no. 1-4; pp. 25 - 33
• Main Authors: Pai, Tzu-Yi, Ho, Ching-Lin, Chen, Shyh-Wei, Lo, Huang-Mu, Sung, Pao-Jui, Lin, Shu-Wen, Lai, Wei-Jia, Tseng, Shih-Chi, Ciou, Shu-Ping, Kuo, Jui-Ling, Kao, Jing-Tang
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.05.2011; Springer; Springer Nature B.V
• Subjects: Air pollution; Airborne particulates; Analysis; Applied sciences; Atmospheric Protection/Air Quality Control/Air Pollution; Climate Change/Climate Change Impacts; Correlation coefficient; Differential equations; Earth and Environmental Science; Environment; Environmental monitoring; Exact sciences and technology; Forecasting techniques; Forecasts and trends; Hydrogeology; Investigations; Local government; Outdoor air quality; Particulate matter; Pollutants; Pollution; Soil Science & Conservation; Studies; System theory; Water Quality/Water Pollution; Asia; Taiwan; Air quality; GM (1, 1); Grey system theory; Hourly particulate matter; PM; Differential equation; Fine particle; Atmospheric pollution forecasting; Aerosols; Air pollution; Urban area; Forecast model
• ISSN: 0049-6979; 1573-2932
• DOI: 10.1007/s11270-010-0564-0

In this study, seven types of first-order and one-variable grey differential equation model (abbreviated as GM (1, 1) model) were used to predict hourly particulate matter (PM) including PM 10 and PM 2.5 concentrations in Banciao City of Taiwan. Their prediction performance was also compared. The results indicated that the minimum mean absolute percentage error (MAPE), mean squared error (MSE), root mean squared error (RMSE), and maximum correlation coefficient ( R ) was 14.10%, 25.62, 5.06, and 0.96, respectively, when predicting PM 10 . When predicting PM 2.5 , the minimum MAPE, MSE, RMSE, and maximum R value of 15.24%, 11.57, 3.40, and 0.93, respectively, could be achieved. All statistical values revealed that the predicting performance of GM (1, 1, x (0) ), GM (1, 1, a ), and GM (1, 1, b ) outperformed other GM (1, 1) models. According to the results, it revealed that GM (1, 1) GM (1, 1) was an efficiently early warning tool for providing PM information to the inhabitants.