A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran
Environmental pollution has mainly been attributed to urbanization and industrial developments across the globe. Air pollution has been marked as one of the major problems of metropolitan areas around the world, especially in Tehran, the capital of Iran, where its administrators and residents have l...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/8/2/99 |
| _version_ | 1818353840990191616 |
|---|---|
| author | Mahmoud Reza Delavar Amin Gholami Gholam Reza Shiran Yousef Rashidi Gholam Reza Nakhaeizadeh Kurt Fedra Smaeil Hatefi Afshar |
| author_facet | Mahmoud Reza Delavar Amin Gholami Gholam Reza Shiran Yousef Rashidi Gholam Reza Nakhaeizadeh Kurt Fedra Smaeil Hatefi Afshar |
| author_sort | Mahmoud Reza Delavar |
| collection | DOAJ |
| description | Environmental pollution has mainly been attributed to urbanization and industrial developments across the globe. Air pollution has been marked as one of the major problems of metropolitan areas around the world, especially in Tehran, the capital of Iran, where its administrators and residents have long been struggling with air pollution damage such as the health issues of its citizens. As far as the study area of this research is concerned, a considerable proportion of Tehran air pollution is attributed to PM<sub>10</sub> and PM<sub>2.5</sub> pollutants. Therefore, the present study was conducted to determine the prediction models to determine air pollutions based on PM<sub>10</sub> and PM<sub>2.5</sub> pollution concentrations in Tehran. To predict the air-pollution, the data related to day of week, month of year, topography, meteorology, and pollutant rate of two nearest neighbors as the input parameters and machine learning methods were used. These methods include a regression support vector machine, geographically weighted regression, artificial neural network and auto-regressive nonlinear neural network with an external input as the machine learning method for the air pollution prediction. A prediction model was then proposed to improve the afore-mentioned methods, by which the error percentage has been reduced and improved by 57%, 47%, 47% and 94%, respectively. The most reliable algorithm for the prediction of air pollution was autoregressive nonlinear neural network with external input using the proposed prediction model, where its one-day prediction error reached 1.79 µg/m<sup>3</sup>. Finally, using genetic algorithm, data for day of week, month of year, topography, wind direction, maximum temperature and pollutant rate of the two nearest neighbors were identified as the most effective parameters in the prediction of air pollution. |
| first_indexed | 2024-12-13T19:15:56Z |
| format | Article |
| id | doaj.art-95e4849cca94483bb08d80c107034a82 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-12-13T19:15:56Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-95e4849cca94483bb08d80c107034a822022-12-21T23:34:17ZengMDPI AGISPRS International Journal of Geo-Information2220-99642019-02-01829910.3390/ijgi8020099ijgi8020099A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of TehranMahmoud Reza Delavar0Amin Gholami1Gholam Reza Shiran2Yousef Rashidi3Gholam Reza Nakhaeizadeh4Kurt Fedra5Smaeil Hatefi Afshar6Center of Excellence in Geomatic Engineering. in Disaster Management, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, P.O. Box 1439951154 Tehran, IranDepartment of GIS, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, P.O. Box 1439951154 Tehran, IranDept. of Transportation Eng., Faculty of Civil & Transportation Engineering, University of Isfahan, P.O. Box 8174673441 Isfahan, IranEnvironmental Scienecs Research Institute, Shahis Beheshti University, P.O. Box 1983969411 Tehran, IranAPL-Professor of Economics and Econometrics, Karlsruhe Institute of Technology, Institute of Economics Econometrics and Statistics, 76049 Karlsruhe, GermanyEnvironmental Software & Services GmbH., A-2352 Vienna, AustriaDepartment of GIS, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, P.O. Box 1439951154 Tehran, IranEnvironmental pollution has mainly been attributed to urbanization and industrial developments across the globe. Air pollution has been marked as one of the major problems of metropolitan areas around the world, especially in Tehran, the capital of Iran, where its administrators and residents have long been struggling with air pollution damage such as the health issues of its citizens. As far as the study area of this research is concerned, a considerable proportion of Tehran air pollution is attributed to PM<sub>10</sub> and PM<sub>2.5</sub> pollutants. Therefore, the present study was conducted to determine the prediction models to determine air pollutions based on PM<sub>10</sub> and PM<sub>2.5</sub> pollution concentrations in Tehran. To predict the air-pollution, the data related to day of week, month of year, topography, meteorology, and pollutant rate of two nearest neighbors as the input parameters and machine learning methods were used. These methods include a regression support vector machine, geographically weighted regression, artificial neural network and auto-regressive nonlinear neural network with an external input as the machine learning method for the air pollution prediction. A prediction model was then proposed to improve the afore-mentioned methods, by which the error percentage has been reduced and improved by 57%, 47%, 47% and 94%, respectively. The most reliable algorithm for the prediction of air pollution was autoregressive nonlinear neural network with external input using the proposed prediction model, where its one-day prediction error reached 1.79 µg/m<sup>3</sup>. Finally, using genetic algorithm, data for day of week, month of year, topography, wind direction, maximum temperature and pollutant rate of the two nearest neighbors were identified as the most effective parameters in the prediction of air pollution.https://www.mdpi.com/2220-9964/8/2/99air pollutionpredictionmachine learningregression SVMgeographically weighted regressionartificial neural networkauto-regressive nonlinear neuralinterpolationgenetic algorithm |
| spellingShingle | Mahmoud Reza Delavar Amin Gholami Gholam Reza Shiran Yousef Rashidi Gholam Reza Nakhaeizadeh Kurt Fedra Smaeil Hatefi Afshar A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran ISPRS International Journal of Geo-Information air pollution prediction machine learning regression SVM geographically weighted regression artificial neural network auto-regressive nonlinear neural interpolation genetic algorithm |
| title | A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran |
| title_full | A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran |
| title_fullStr | A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran |
| title_full_unstemmed | A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran |
| title_short | A Novel Method for Improving Air Pollution Prediction Based on Machine Learning Approaches: A Case Study Applied to the Capital City of Tehran |
| title_sort | novel method for improving air pollution prediction based on machine learning approaches a case study applied to the capital city of tehran |
| topic | air pollution prediction machine learning regression SVM geographically weighted regression artificial neural network auto-regressive nonlinear neural interpolation genetic algorithm |
| url | https://www.mdpi.com/2220-9964/8/2/99 |
| work_keys_str_mv | AT mahmoudrezadelavar anovelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT amingholami anovelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT gholamrezashiran anovelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT yousefrashidi anovelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT gholamrezanakhaeizadeh anovelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT kurtfedra anovelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT smaeilhatefiafshar anovelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT mahmoudrezadelavar novelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT amingholami novelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT gholamrezashiran novelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT yousefrashidi novelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT gholamrezanakhaeizadeh novelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT kurtfedra novelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran AT smaeilhatefiafshar novelmethodforimprovingairpollutionpredictionbasedonmachinelearningapproachesacasestudyappliedtothecapitalcityoftehran |