Modeling Haze Problems in the North of Thailand using Logistic Regression
At present, air pollution is a major problem in the upper northern region of Thailand. Air pollutants have an effect on human health, the economy and the traveling industry. The severity of this problem clearly appears every year during the dry season, from February to April. In particular it become...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
ITB Journal Publisher
2014-07-01
|
| Series: | Journal of Mathematical and Fundamental Sciences |
| Subjects: | |
| Online Access: | http://journals.itb.ac.id/index.php/jmfs/article/view/827 |
| _version_ | 1811278007257530368 |
|---|---|
| author | Busayamas Pimpunchat Khwansiri Sirimangkhala Suwannee Junyapoon |
| author_facet | Busayamas Pimpunchat Khwansiri Sirimangkhala Suwannee Junyapoon |
| author_sort | Busayamas Pimpunchat |
| collection | DOAJ |
| description | At present, air pollution is a major problem in the upper northern region of Thailand. Air pollutants have an effect on human health, the economy and the traveling industry. The severity of this problem clearly appears every year during the dry season, from February to April. In particular it becomes very serious in March, especially in Chiang Mai province where smoke haze is a major issue. This study looked into related data from 2005-2010 covering eight principal parameters: PM10 (particulate matter with a diameter smaller than 10 micrometer), CO (carbon monoxide), NO2 (nitrogen dioxide), SO2 (sulphur dioxide), RH (relative humidity), NO (nitrogen oxide), pressure, and rainfall. Overall haze problem occurrence was calculated from a logistic regression model. Its dependence on the eight parameters stated above was determined for design conditions using the correlation coefficients with PM10. The proposed overall haze problem modeling can be used as a quantitative assessment criterion for supporting decision making to protect human health. This study proposed to predict haze problem occurrence in 2011. The agreement of the results from the mathematical model with actual measured PM10 concentration data from the Pollution Control Department was quite satisfactory. |
| first_indexed | 2024-04-13T00:26:59Z |
| format | Article |
| id | doaj.art-b1578ba7f0904a37aa9458d049b59d1f |
| institution | Directory Open Access Journal |
| issn | 2337-5760 2338-5510 |
| language | English |
| last_indexed | 2024-04-13T00:26:59Z |
| publishDate | 2014-07-01 |
| publisher | ITB Journal Publisher |
| record_format | Article |
| series | Journal of Mathematical and Fundamental Sciences |
| spelling | doaj.art-b1578ba7f0904a37aa9458d049b59d1f2022-12-22T03:10:34ZengITB Journal PublisherJournal of Mathematical and Fundamental Sciences2337-57602338-55102014-07-0146218319310.5614/j.math.fund.sci.2014.46.2.7Modeling Haze Problems in the North of Thailand using Logistic RegressionBusayamas Pimpunchat0Khwansiri Sirimangkhala1Suwannee Junyapoon2Industrial Mathematics Research Unit & Department of Mathematics, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, ThailandIndustrial Mathematics Research Unit & Department of Mathematics, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, ThailandDepartment of Chemistry, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, ThailandAt present, air pollution is a major problem in the upper northern region of Thailand. Air pollutants have an effect on human health, the economy and the traveling industry. The severity of this problem clearly appears every year during the dry season, from February to April. In particular it becomes very serious in March, especially in Chiang Mai province where smoke haze is a major issue. This study looked into related data from 2005-2010 covering eight principal parameters: PM10 (particulate matter with a diameter smaller than 10 micrometer), CO (carbon monoxide), NO2 (nitrogen dioxide), SO2 (sulphur dioxide), RH (relative humidity), NO (nitrogen oxide), pressure, and rainfall. Overall haze problem occurrence was calculated from a logistic regression model. Its dependence on the eight parameters stated above was determined for design conditions using the correlation coefficients with PM10. The proposed overall haze problem modeling can be used as a quantitative assessment criterion for supporting decision making to protect human health. This study proposed to predict haze problem occurrence in 2011. The agreement of the results from the mathematical model with actual measured PM10 concentration data from the Pollution Control Department was quite satisfactory.http://journals.itb.ac.id/index.php/jmfs/article/view/827forecastinghaze problemmultivariate logistic regressionmathematical modelPM10 |
| spellingShingle | Busayamas Pimpunchat Khwansiri Sirimangkhala Suwannee Junyapoon Modeling Haze Problems in the North of Thailand using Logistic Regression Journal of Mathematical and Fundamental Sciences forecasting haze problem multivariate logistic regression mathematical model PM10 |
| title | Modeling Haze Problems in the North of Thailand using Logistic Regression |
| title_full | Modeling Haze Problems in the North of Thailand using Logistic Regression |
| title_fullStr | Modeling Haze Problems in the North of Thailand using Logistic Regression |
| title_full_unstemmed | Modeling Haze Problems in the North of Thailand using Logistic Regression |
| title_short | Modeling Haze Problems in the North of Thailand using Logistic Regression |
| title_sort | modeling haze problems in the north of thailand using logistic regression |
| topic | forecasting haze problem multivariate logistic regression mathematical model PM10 |
| url | http://journals.itb.ac.id/index.php/jmfs/article/view/827 |
| work_keys_str_mv | AT busayamaspimpunchat modelinghazeproblemsinthenorthofthailandusinglogisticregression AT khwansirisirimangkhala modelinghazeproblemsinthenorthofthailandusinglogisticregression AT suwanneejunyapoon modelinghazeproblemsinthenorthofthailandusinglogisticregression |