Comparative evaluation of backpropagation neural network and genetic algorithm-backpropagation neural network models for PM2.5 concentration prediction based on aerosol optical depth, meteorological factors, and air pollutants

• Published in: Journal of applied remote sensing Vol. 18; no. 1; p. 012006
• Main Authors: Gu, Jilin, Liang, Shuang, Song, Qiao, Li, Yuwei, Wang, Yiwei, Guo, Shumin
• Format: Journal Article
• Language: English
• Published: Society of Photo-Optical Instrumentation Engineers 01.01.2024
• Subjects: genetic algorithm-backpropagation neural network; backpropagation neural network; PM; aerosol optical depth
• ISSN: 1931-3195; 1931-3195
• DOI: 10.1117/1.JRS.18.012006

Fine particles with an aerodynamic diameter ≤2.5  μm are called PM2.5, and accurate prediction of PM2.5 concentration can help prevent the harmful effects of heavy pollution on humans. At present, the distribution of ground-based PM2.5 monitoring stations in China’s cities is relatively sparse. Hence, the aerosol optical depth (AOD) obtained from satellite remote sensing provides an effective means for large-scale routine PM2.5 monitoring. In this study, the multi-angle implementation of atmospheric correction AOD (1 km resolution) product from the moderate resolution imaging spectroradiometer (MODIS), meteorological factors, and ground measurements of daily PM2.5 concentrations from 2016 to 2020 for Dalian were input into a backpropagation neural network (BPNN) to predict PM2.5 concentrations. To improve the prediction accuracy and stability, a genetic algorithm (GA)-optimized BPNN was further established based on the BPNN to achieve a comparative PM2.5 concentration prediction. Results showed that the BPNN and GA-BPNN achieved the PM2.5 concentration by integrating AOD, meteorological factors, and air pollutants with the model test set R2 of 0.77 and 0.83 and root mean square error (RMSE) of 11.83 and 9.80  μg m  −  3, respectively. GA-BPNN decreased the SDRMSE from 0.44 to 0.23  μg m  −  3 compared with BPNN and improved the model stability. The spatial distribution of annual averaged estimated PM2.5 was predicted using GA-BPNN in Dalian from 2016 to 2020. The spatial distribution of PM2.5 concentrations was generally consistent over 5 years, and the PM2.5 concentrations exhibited an overall decreasing trend. The BPNN before and after optimization achieved longer-term interannual PM2.5 daily concentration prediction, and the GA-BPNN had a better prediction effect for extreme values, handled complex fuzzy mapping relationships, and had lower computational complexity. Hence, GA-BPNN was found to be more suitable for practical applications with more advantages for PM2.5 concentration prediction than BPNN.