Abstract PM2.5 is the main component of most haze, and the presence of high concentrations of PM2.5 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 PM2.5. Traditional PM2.5 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 PM2.5 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 PM2.5 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 (O3, CO, NO2, SO2, PM10, and PM2.5) were used to establish PM2.5 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 PM2.5 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 PM2.5 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 PM2.5 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 PM2.5 concentration are close to the areas with serious pollution in Hebei Province by analyzing the PM2.5 map of Beijing, and area transport and human activities are important sources of air pollution.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Estimation of PM2.5 concentrations with high spatiotemporal resolution in Beijing using the ERA5 dataset and machine learning models


    Beteiligte:
    Wang, Zhihao (Autor:in) / Chen, Peng (Autor:in) / Wang, Rong (Autor:in) / An, Zhiyuan (Autor:in) / Qiu, Liangcai (Autor:in)

    Erschienen in:

    Advances in Space Research ; 71 , 8 ; 3150-3165


    Erscheinungsdatum :

    2022-12-07


    Format / Umfang :

    16 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Comparison of ZTD derived from CARRA, ERA5 and ERA5-Land over the Greenland based on GNSS

    Jiang, Chunhua / Gao, Xiang / Wang, Shuaimin et al. | Elsevier | 2023



    Performance of ERA5 data in retrieving precipitable water vapor over Hong Kong

    Wang, Zhihao / Chen, Peng / Wang, Rong et al. | Elsevier | 2022


    Investigation and pre-processing of CLaMP mlaware dataset for machine learning models

    Singh, Priyanka / Borgohain, Samir Kumar / Kumar, Jayendra | IEEE | 2022


    Performance of ERA5 data in retrieving Precipitable Water Vapour over East African tropical region

    Ssenyunzi, Richard Cliffe / Oruru, Bosco / D’ujanga, Florence Mutonyi et al. | Elsevier | 2020