Air pollution is a key environmental and social issue and it is also a complex problem posing multiple challenges in terms of management and mitigation of pollutants. The evaluation of the status of air quality is based mainly on ambient air measurements. Although the emissions of principal air pollutants are highly regulated, there is a lack of information about the real extent of emissions generated by the traffic and made difficult the quantification of the effects of policies and measures to reduce air pollution. To tackle these challenges, local air pollution measurements near main streets, based on small IoT devices became necessary. The aim of the paper is to present the way in which low-cost sensors in combination with Artificial Intelligence algorithms could be used for prediction of PM10 and PM-2.5 concentration. The data were collected using IoT devices based on Optical Particle Counter technologies, statistically analyzed and corrected (using a specific algorithm) to reduce the influence of the air humidity. Comparison with measurement from reference station were presented. For PM10 and PM-2.5 concentration forecasting was developed an ARIMA algorithm which was tested for time series registered in Bucharest. The results show that in 89% of cases the predicted values are within the accepted uncertainty limit, while the Pearson correlation coefficients have significant values.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    PMs concentration forecasting using ARIMA algorithm


    Contributors:


    Publication date :

    2020-05-01


    Size :

    270686 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Forecasting Hydroelectric Dam Energy Production Using a Hybrid Ann-Arima Model

    Ioannou, Konstantinos / Zaimes, George N. / Emmanouloudis, Dimitrios et al. | HENRY – Federal Waterways Engineering and Research Institute (BAW) | 2012

    Free access

    Highway Traffic Volume Forecasting Based on Seasonal ARIMA Model

    Tong, Mingrong / Xue, Hengxin | ASCE | 2008


    Forecasting Short-term Container Vessel Traffic Volume Using Hybrid ARIMA-NN Model

    Negar Sadeghi Gargari / Hassan Akbari / Roozbeh Panahi | DOAJ | 2019

    Free access