Modelling of PM10 Pollution in Karatay District of Konya with Artificial Neural Networks
| Autor: | Ayturan, Yasin Akın, Öztürk, Ali, Ayturan, Zeynep Cansu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: | |
| Zdroj: | Volume: 12, Issue: 3 256-263 Journal of International Environmental Application and Science BASE-Bielefeld Academic Search Engine zcayturan |
| ISSN: | 1307-0428 2636-7661 |
| Popis: | Air pollution is one of the most significant issues of human being facednowadays because it can create adverse effects on both health of human andother livings. There are several air pollutants which are considered asdangerous such as sulphur dioxide (SO2), nitrous oxide (NOx),carbon monoxide (CO), volatile organic compounds (VOC) and particulate matter(PM). Particulate matter is one the most significant air pollutants because itmay create respiratory, cardiological and pulmonary problems by inhalation bynose on humans. Also, heavy metals and hydrocarbons may be adsorbed on PMsurface, so it is considered as carcinogenic by World Health Organization(WHO). When all these negative effects of PM are taken into consideration, itis important that PM future concentration should be determined for takingprecautions. PM is classified according to the diameter of the particles and PM10is described as particulates which has diameter smaller than 10 micrometres. Inthis study, PM10 pollution was predicted with artificial neuralnetwork (ANN) for Karatay district of Konya. ANN includes interconnectedstructures that can make parallel computations. Several meteorological factorsand air pollutant concentrations was provided by database of Ministry ofEnvironment and Urbanisation belonging to autumn period of 2016 such as SO2concentration, NO concentration, NOx concentration, NO2concentration, CO concentration, O3 concentration, wind speed,temperature, relative humidity, air pressure, wind direction and previous day’sPM10 concentration. These parameters were used in the model as inputparameters and PM10 concentration for one day later was used as anoutput parameter. Prediction performance of the obtained model was verypromising when the similar studies are examined. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|