Search Results (2)

Accurate and fine-grained individual air quality index (IAQI) prediction is the basis of air quality index (AQI), which is of great significance for air quality control and human health. Traditional approaches, such as time series, recurrent neural network or graph convolutional network, cannot effectively integrate spatial-temporal and meteorological factors and manage the dynamic edge relationship among scattered monitoring stations. In this paper, a ST-CCN-IAQI model is proposed based on spatial-temporal causal convolution networks. Both the spatial effects of multi-source air pollutants and meteorological factors were considered via spatial attention mechanism. Time-dependent features in the causal convolution network were extracted by stacked dilated convolution and time attention. All the hyper-parameters in ST-CCN-IAQI were tuned by Bayesian optimization. Shanghai air monitoring station data were employed with a series of baselines (AR, MA, ARMA, ANN, SVR, GRU, LSTM and ST-GCN). Final results showed that: (1) For a single station, the RMSE and MAE values of ST-CCN-IAQI were 9.873 and 7.469, decreasing by 24.95% and 16.87% on average, respectively. R² was 0.917, with an average 5.69% improvement; (2) For all nine stations, the mean RMSE and MAE of ST-CCN-IAQI were 9.849 and 7.527, respectively, and the R² value was 0.906. (3) Shapley analysis showed PM₁₀, humidity and NO₂ were the most influencing factors in ST-CCN-IAQI. The Friedman test, under different resampling, further confirmed the advantage of ST-CCN-IAQI. The ST-CCN-IAQI provides a promising direction for fine-grained IAQI prediction. Full article

Air pollutants have been investigated in many studies, but the variations of atmospheric pollutants and their relationship with rainwater chemistry are not well studied. In the present study, the criteria atmospheric pollutants in nine monitoring stations and rainwater chemistry were analyzed in karst Guiyang city, since the time when the Chinese Ambient Air Quality Standards (CAAQS, third revision) were published. Based on the three-year daily concentration dataset of SO₂, NO₂, CO, PM₁₀ and PM_2.5, although most of air pollutant concentrations were within the limit of CAAQS III-Grade II standard, the significant spatial variations and relatively heavy pollution were found in downtown Guiyang. Temporally, the average concentrations of almost all air pollutants (except for CO) decreased during three years at all stations. Ratios of PM_2.5/PM₁₀ in non- and episode days reflected the different contributions of fine and coarse particles on particulate matter in Guiyang, which was influenced by the potential meteorological factors and source variations. According to the individual air quality index (IAQI), the seasonal variations of air quality level were observed, that is, IAQI values of air pollutants were higher in winter (worst air quality) and lower in summer (best air quality) due to seasonal variations in emission sources. The unique IAQI variations were found during the Chinese Spring Festival. Air pollutant concentrations are also influenced by meteorological parameters, in particular, the rainfall amount. The air pollutants are well scoured by the rainfall process and can significantly affect rainwater chemistry, such as SO₄²⁻, NO₃⁻, Mg²⁺, and Ca²⁺, which further alters the acidification/alkalization trend of rainwater. The equivalent ratios of rainwater SO₄²⁻/NO₃⁻ and Mg²⁺/Ca²⁺ indicated the significant contribution of fixed emission sources (e.g., coal combustion) and carbonate weathering-influenced particulate matter on rainwater chemistry. These findings provide scientific support for air pollution management and rainwater chemistry-related environmental issues. Full article