Research of low-cost air quality monitoring models with different machine learning algorithms

Abstract

Abstract. To improve the performance of the calibration model for the air quality monitoring, a low-cost multi-parameter air quality monitoring system (LCS) based on different machine learning algorithms is proposed. The LCS can measure particulate matter (PM2.5 and PM10) and gas pollutants (SO2, NO2, CO and O3) simultaneously. The multi-input multi-output (MIMO) prediction model is developed based on the original signals of the sensors, ambient temperature (T) and relative humidity (RH), and the measurements of the reference instrumentations. The performance of the different algorithms (RF, MLR, KNN, BP, GA–BP) with parameters such as determination coefficient R2, root mean square error (RMSE), and mean absolute error (MAE) are compared and discussed. Using these methods, the R2 of the algorithms (RF, MLR, KNN, BP, GA–BP) for the PM is in the range 0.68–0.99; the RMSE values of PM2.5 and PM10 are within 2.36–18.68 and 4.55–45.05 µg m−3, respectively; the MAE values of PM2.5 and PM10 are within 1.44–12.80 and 3.21–23.20 µg m−3, respectively. The R2 of the algorithms (RF, MLR, KNN, BP, GA–BP) for the gas pollutants (O3, CO and NO2) is within 0.70–0.99; the RMSE values for these pollutants are 4.05–17.79 µg m−3, 0.02–0.18 mg m−3, 2.88–14.54 µg m−3, respectively; the MAE values for these pollutants are 2.76–13.46 µg m−3, 0.02–0.19 mg m−3, 1.84–11.08 µg m−3, respectively. The R2 of the algorithms (RF, KNN, BP, GA–BP, except for MLR) for SO2 is within 0.27–0.97, the RMSE value is in the range 0.64–5.37 µg m−3, and the MAE value is in the range 0.39–4.24 µg m−3. These measurements are consistent with the national environmental protection standard requirement of China, and the LCS based on the machine learning algorithms can be used to predict the concentrations of PM and gas pollution.