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

Wang, Gang; Yu, Chunlai; Guo, Kai; Guo, Haisong; Wang, Yibo

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 (PMinline-formula2.5 and PMinline-formula10) and gas pollutants (SOinline-formula2, NOinline-formula2, CO and Oinline-formula3) simultaneously. The multi-input multi-output (MIMO) prediction model is developed based on the original signals of the sensors, ambient temperature (inline-formulaT) 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 inline-formulaR2, root mean square error (RMSE), and mean absolute error (MAE) are compared and discussed. Using these methods, the inline-formulaR2 of the algorithms (RF, MLR, KNN, BP, GA–BP) for the PM is in the range 0.68–0.99; the RMSE values of PMinline-formula2.5 and PMinline-formula10 are within 2.36–18.68 and 4.55–45.05 inline-formulaµg minline-formula−3, respectively; the MAE values of PMinline-formula2.5 and PMinline-formula10 are within 1.44–12.80 and 3.21–23.20 inline-formulaµg minline-formula−3, respectively. The inline-formulaR2 of the algorithms (RF, MLR, KNN, BP, GA–BP) for the gas pollutants (Oinline-formula3, CO and NOinline-formula2) is within 0.70–0.99; the RMSE values for these pollutants are 4.05–17.79 inline-formulaµg minline-formula−3, 0.02–0.18 mg minline-formula−3, 2.88–14.54 inline-formulaµg minline-formula−3, respectively; the MAE values for these pollutants are 2.76–13.46 inline-formulaµg minline-formula−3, 0.02–0.19 mg minline-formula−3, 1.84–11.08 inline-formulaµg minline-formula−3, respectively. The inline-formulaR2 of the algorithms (RF, KNN, BP, GA–BP, except for MLR) for SOinline-formula2 is within 0.27–0.97, the RMSE value is in the range 0.64–5.37 inline-formulaµg minline-formula−3, and the MAE value is in the range 0.39–4.24 inline-formulaµg minline-formula−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.

Zitieren

Zitierform:

Wang, Gang / Yu, Chunlai / Guo, Kai / et al: Research of low-cost air quality monitoring models with different machine learning algorithms. 2024. Copernicus Publications.

Zugriffsstatistik

Gesamt:
Volltextzugriffe:
Metadatenansicht:
12 Monate:
Volltextzugriffe:
Metadatenansicht:

Grafik öffnen

Rechte

Rechteinhaber: Gang Wang et al.

Nutzung und Vervielfältigung:

Export