Search

PM 2.5 is the main component of most haze, and the presence of high concentrations of PM 2.5 in the air for an extended time can cause serious effects on human health, so there is an urgent need for research work related to PM 2.5. Traditional PM 2.5 monitoring uses ground-based monitoring stations with low spatial resolution. Other studies have retrieved the Moderate Resolution Imaging Spectroradiometer aerosol optical depth product by the dark-target algorithm. However, the estimated PM 2.5 concentration on the ground will produce missing values, which will lead to the reduction of spatial and temporal resolution. Based on this, this study proposes a machine learning algorithm to estimate PM 2.5 by using the fifth generation reanalysis (ERA5) data set published by the European Center for Medium-range Weather Forecasts (ECMWF). In this study, two different methods of back propagation neural network (BPNN) and random forest (RF) were used to develop the models. Firstly, the meteorological parameters (precipitable water vapor, water vapor pressure and relative humidity, etc.) and pollution parameters (O 3 , CO, NO 2 , SO 2 , PM 10 , and PM 2.5) were used to establish PM 2.5 model in 2021. The results showed that the R2 and RMSE for BPNN and RF were 0.94/0.96 and 10.37/8.77 µg/m3, respectively. Then, due to the lack and the low spatial resolution of the pollution parameters, using only the ERA5 meteorological data with the high spatiotemporal resolution to develop the PM 2.5 model in winter, the R2 of the RF model (0.93) was 0.05 higher and the RMSE (12.50 µg/m3) was 4.19 µg/m3 lower than that of the BPNN model, which indicates that it is feasible to develop the PM 2.5 model using only meteorological parameters. Finally, using the RF model of the second stage and ERA5 meteorological data with a spatial resolution of 0.05° (obtained by cubic spline interpolation) to generate the hourly PM 2.5 map of Beijing and compare it with China High Air Pollutants dataset, the R2 and RMSE of Beijing were 0.78 µg/m3 and 14.85 µg/m3, respectively. On this basis, it is found that the areas with high PM 2.5 concentration are close to the areas with serious pollution in Hebei Province by analyzing the PM 2.5 map of Beijing, and area transport and human activities are important sources of air pollution. [ABSTRACT FROM AUTHOR]

Background: Quantifying CO2 emissions from cities is of great importance because cities contribute more than 70% of the global total CO2 emissions. As the largest urbanized megalopolis region in northern China, the Beijing-Tianjin-Hebei (Jing-Jin-Ji, JJJ) region (population: 112.7 million) is under considerable pressure to reduce carbon emissions. Despite the several emission inventories covering the JJJ region, a comprehensive evaluation of the CO2 emissions at the prefectural city scale in JJJ is still limited, and this information is crucial to implementing mitigation strategies. Results: Here, we collected and analyzed 8 published emission inventories to assess the emissions and uncertainty at the JJJ city level. The results showed that a large discrepancy existed in the JJJ emissions among downscaled country-level emission inventories, with total emissions ranging from 657 to 1132 Mt CO2 (or 849 ± 214 for mean ± standard deviation (SD)) in 2012, while emission estimates based on provincial-level data estimated emissions to be 1038 and 1056 Mt. Compared to the mean emissions of city-data-based inventories (989 Mt), provincial-data-based inventories were 6% higher, and national-data-based inventories were 14% lower. Emissions from national-data-based inventories were 53–75% lower in the high-emitting industrial cities of Tangshan and Handan, while they were 47–160% higher in Beijing and Tianjin than those from city-data-based inventories. Spatially, the emissions pattern was consistent with the distribution of urban areas, and urban emissions in Beijing contributed 50–70% of the total emissions. Higher emissions from Beijing and Tianjin resulted in lower estimates of prefectural cities in Hebei for some national inventories. Conclusions: National-level data-based emission inventories produce large differences in JJJ prefectural city-level emission estimates. The city-level statistics data-based inventories produced more consistent estimates. The consistent spatial distribution patterns recognized by these inventories (such as high emissions in southern Beijing, central Tianjin and Tangshan) potentially indicate areas with robust emission estimates. This result could be useful in the efficient deployment of monitoring instruments, and if proven by such measurements, it will increase our confidence in inventories and provide support for policy makers trying to reduce emissions in key regions. [ABSTRACT FROM AUTHOR]