Characterization of the Concentrations of Volatile Organic Compounds in the Romanian Littoral using General Regression Neural Networks: A Case Study

Abstract

In the last decade, preserving air quality in the northern Romanian Littoral has become a national priority. In order to monitor pollution, benzene, toluene, ortho-, meta-, and para-xylene, ethylbenzene, and styrene were determined at six monitoring sites in three industrial and three urban areas. The sampling was done by an active method and the analysis by gas chromatography. The statistical analysis demonstrated that the concentrations of the volatile organic compounds were under the limits established by the European Union's laws and that the pollutant distributions were asymmetric. Models were proposed for the concentrations of the volatile organic Downloaded by [New York University] at 09:48 07 June 20152 compounds, using the general regression neural network, with wind speed, air temperature, and humidity as regressors. The theoretical fit well with the experimental results, showing that the model is an effective alternative to conventional approaches.

Assessing Benzene and TVOC Pollution and the Carcinogenic and Noncarcinogenic Risks to Workers in an Industrial Plant in Southeastern Romania

“…Many researchers have noted that volatile pollutants could accumulate in urban and suburban areas and roads near industrial oil refinery parks [ 2 , 4 , 5 , 11 , 20 , 39 , 41 , 88 , 89 , 90 ]. Zhang et al [ 89 ] indicate that the emission rates of Chinese refineries have consistently exceeded those of certain developed countries with traditions in crude oil processing, including in European countries [ 2 , 5 ] and the northern and southern states of the USA.…”

“…Total volatile organic compounds, expressed as non-methane volatile organic compounds (NMVOCs), including aromatic hydrocarbons (benzene, toluene, ethyl-benzene, and ortho-, meta-, and para-xylene, etc.) with moderate volatility, are found in different concentrations in urban and suburban regions [5][6][7][8][9][10], shoreline areas [11], and industrial zones [12][13][14][15].…”

Statistical assessment and modeling of benzene level in atmosphere in Timiş County, Romania

“…The policies implemented at European, national and sectoral levels have led to a decrease in the emissions levels of many pollutants and improvement of air quality throughout the European continent (EEA 2017. Several studies show that in the last decade, in Romania, emissions of certain pollutants decreased and, implicitly, the exposure to various inorganic or organic compounds (CO, SO 2 , benzene, or derived monoaromatic compounds) diminished (Bărbulescu and Barbeş 2016, 2017a, 2017bBărbulescu 2016). Other studies show that in the atmosphere still exist appreciable amounts of suspended particles (classified PM 10 and PM 2.5 ).…”

Do the time series statistical properties influence the goodness of fit of GRNN models? Study on financial series

“…The GRNN have been applied to predicting time series in various fields including financial time series, 17 signal processing, 16 civil engineering, 18 agriculture, 19 atmospheric pollution, 20 hydrology, 21 and health sciences. 22 In this paper, we provide the results of the comparison of performances of the GRNN models built for the monthly closing values of Bucharest Exchange Trading (BET), registered in the period from October 2000 to September 2014 (taken from the website of Bucharest Stock Exchange, ie, http://www.bvb.ro).…”