Artificial neural network forecast application for fine particulate matter concentration using meteorological data
Most parts of the urban areas are faced with the problem of floating fine particulate matter. Therefore, it is crucial to estimate the amounts of fine particulate matter concentrations through the urban atmosphere. In this research, an artificial neural network technique was utilized to model the PM...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
GJESM Publisher
2017-09-01
|
| Series: | Global Journal of Environmental Science and Management |
| Subjects: | |
| Online Access: | http://www.gjesm.net/article_23079_e3b575506205de32a43eea8e244ad182.pdf |
| _version_ | 1826841741712424960 |
|---|---|
| author | M. Memarianfard A.M. Hatami M. Memarianfard |
| author_facet | M. Memarianfard A.M. Hatami M. Memarianfard |
| author_sort | M. Memarianfard |
| collection | DOAJ |
| description | Most parts of the urban areas are faced with the problem of floating fine particulate matter. Therefore, it is crucial to estimate the amounts of fine particulate matter concentrations through the urban atmosphere. In this research, an artificial neural network technique was utilized to model the PM2.5 dispersion in Tehran City. Factors which are influencing the predicted value consist of weather-related and air pollution-related data, i.e. wind speed, humidity, temperature, SO2, CO, NO2, and PM2.5 as target values. These factors have been considered in 19 measuring stations (zones) over urban area across Tehran City during four years, from March 2011 to March 2015. The results indicate that the network with hidden layer including six neurons at training epoch 113, has the best performance with the lowest error value (MSE=0.049438) on considering PM2.5 concentrations across metropolitan areas in Tehran. Furthermore, the “R” value for regression analysis of training, validation, test, and all data are 0.65898, 0.6419, 0.54027, and 0.62331, respectively. This study also represents the artificial neural networks have satisfactory implemented for resolving complex patterns in the field of air pollution. |
| first_indexed | 2024-12-14T19:30:48Z |
| format | Article |
| id | doaj.art-5b985be99bf740d5854afe7682fdc08e |
| institution | Directory Open Access Journal |
| issn | 2383-3572 2383-3866 |
| language | English |
| last_indexed | 2025-02-16T13:07:20Z |
| publishDate | 2017-09-01 |
| publisher | GJESM Publisher |
| record_format | Article |
| series | Global Journal of Environmental Science and Management |
| spelling | doaj.art-5b985be99bf740d5854afe7682fdc08e2025-02-02T15:36:40ZengGJESM PublisherGlobal Journal of Environmental Science and Management2383-35722383-38662017-09-013333334010.22034/gjesm.2017.03.03.01023079Artificial neural network forecast application for fine particulate matter concentration using meteorological dataM. Memarianfard0A.M. Hatami1M. Memarianfard2Department of Civil Engineering, K.N. Toosi University of Technology, Tehran, IranDepartment of Civil Engineering, K.N. Toosi University of Technology, Tehran, IranDepartment of Civil Engineering, K.N. Toosi University of Technology, Tehran, IranMost parts of the urban areas are faced with the problem of floating fine particulate matter. Therefore, it is crucial to estimate the amounts of fine particulate matter concentrations through the urban atmosphere. In this research, an artificial neural network technique was utilized to model the PM2.5 dispersion in Tehran City. Factors which are influencing the predicted value consist of weather-related and air pollution-related data, i.e. wind speed, humidity, temperature, SO2, CO, NO2, and PM2.5 as target values. These factors have been considered in 19 measuring stations (zones) over urban area across Tehran City during four years, from March 2011 to March 2015. The results indicate that the network with hidden layer including six neurons at training epoch 113, has the best performance with the lowest error value (MSE=0.049438) on considering PM2.5 concentrations across metropolitan areas in Tehran. Furthermore, the “R” value for regression analysis of training, validation, test, and all data are 0.65898, 0.6419, 0.54027, and 0.62331, respectively. This study also represents the artificial neural networks have satisfactory implemented for resolving complex patterns in the field of air pollution.http://www.gjesm.net/article_23079_e3b575506205de32a43eea8e244ad182.pdfAir pollutionArtificial neural network (ANN)Meteorological dataPM2.5 concentrationTehran City |
| spellingShingle | M. Memarianfard A.M. Hatami M. Memarianfard Artificial neural network forecast application for fine particulate matter concentration using meteorological data Global Journal of Environmental Science and Management Air pollution Artificial neural network (ANN) Meteorological data PM2.5 concentration Tehran City |
| title | Artificial neural network forecast application for fine particulate matter concentration using meteorological data |
| title_full | Artificial neural network forecast application for fine particulate matter concentration using meteorological data |
| title_fullStr | Artificial neural network forecast application for fine particulate matter concentration using meteorological data |
| title_full_unstemmed | Artificial neural network forecast application for fine particulate matter concentration using meteorological data |
| title_short | Artificial neural network forecast application for fine particulate matter concentration using meteorological data |
| title_sort | artificial neural network forecast application for fine particulate matter concentration using meteorological data |
| topic | Air pollution Artificial neural network (ANN) Meteorological data PM2.5 concentration Tehran City |
| url | http://www.gjesm.net/article_23079_e3b575506205de32a43eea8e244ad182.pdf |
| work_keys_str_mv | AT mmemarianfard artificialneuralnetworkforecastapplicationforfineparticulatematterconcentrationusingmeteorologicaldata AT amhatami artificialneuralnetworkforecastapplicationforfineparticulatematterconcentrationusingmeteorologicaldata AT mmemarianfard artificialneuralnetworkforecastapplicationforfineparticulatematterconcentrationusingmeteorologicaldata |