Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information
Abstract Using statistical models, the average hourly ozone (O3) concentration was predicted from seven meteorological variables (Pearson correlation coefficient, R = 0.87–0.90), with solar radiation and temperature being the most important predictors. This can serve to predict O3 for cities with re...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2021-06-01
|
| Series: | Aerosol and Air Quality Research |
| Subjects: | |
| Online Access: | https://doi.org/10.4209/aaqr.200471 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862842516832256 |
|---|---|
| author | Felipe Cifuentes Angel Gálvez Carlos M. González Mauricio Orozco-Alzate Beatriz H. Aristizábal |
| author_facet | Felipe Cifuentes Angel Gálvez Carlos M. González Mauricio Orozco-Alzate Beatriz H. Aristizábal |
| author_sort | Felipe Cifuentes |
| collection | DOAJ |
| description | Abstract Using statistical models, the average hourly ozone (O3) concentration was predicted from seven meteorological variables (Pearson correlation coefficient, R = 0.87–0.90), with solar radiation and temperature being the most important predictors. This can serve to predict O3 for cities with real time meteorological data but no pollutant sensing capability. Incorporating other pollutants (PM2.5, SO2, and CO) into the models did not significantly improve O3 prediction (R = 0.91–0.94). Predictions were also made for PM2.5, but results could not reflect its peaks and outliers resulting from local sources. Here we make a comparative analysis of three different statistical predictor models: (1) Multiple Linear Regression (MLR), (2) Support Vector Regression (SVR), and (3) Artificial Neuronal Networks (ANNs) to forecast hourly O3 and PM2.5 concentrations in a mid-sized Andean city (Manizales, Colombia). The study also analyzes the effect of using different sets of predictor variables: (1) Spearman coefficients higher than ± 0.3, (2) variables with loadings higher than ± 0.3 from a principal component analysis (PCA), (3) only meteorological variables, and (4) all available variables. In terms of the O3 forecast, the best model was obtained using ANNs with all the available variables as predictors. The methodology could serve other researchers for implementing statistical forecasting models in their regions with limited pollutant information. |
| format | Article |
| id | doaj-art-c43af898295d4ec0833e2e643fdaea8f |
| institution | Kabale University |
| issn | 1680-8584 2071-1409 |
| language | English |
| publishDate | 2021-06-01 |
| publisher | Springer |
| record_format | Article |
| series | Aerosol and Air Quality Research |
| spelling | doaj-art-c43af898295d4ec0833e2e643fdaea8f2025-02-09T12:21:26ZengSpringerAerosol and Air Quality Research1680-85842071-14092021-06-0121912110.4209/aaqr.200471Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant InformationFelipe Cifuentes0Angel Gálvez1Carlos M. González2Mauricio Orozco-Alzate3Beatriz H. Aristizábal4Hydraulic Engineering and Environmental Research Group, Universidad Nacional de Colombia Sede ManizalesHydraulic Engineering and Environmental Research Group, Universidad Nacional de Colombia Sede ManizalesHydraulic Engineering and Environmental Research Group, Universidad Nacional de Colombia Sede ManizalesDepartment of Informatics and Computing, Universidad Nacional de Colombia Sede ManizalesHydraulic Engineering and Environmental Research Group, Universidad Nacional de Colombia Sede ManizalesAbstract Using statistical models, the average hourly ozone (O3) concentration was predicted from seven meteorological variables (Pearson correlation coefficient, R = 0.87–0.90), with solar radiation and temperature being the most important predictors. This can serve to predict O3 for cities with real time meteorological data but no pollutant sensing capability. Incorporating other pollutants (PM2.5, SO2, and CO) into the models did not significantly improve O3 prediction (R = 0.91–0.94). Predictions were also made for PM2.5, but results could not reflect its peaks and outliers resulting from local sources. Here we make a comparative analysis of three different statistical predictor models: (1) Multiple Linear Regression (MLR), (2) Support Vector Regression (SVR), and (3) Artificial Neuronal Networks (ANNs) to forecast hourly O3 and PM2.5 concentrations in a mid-sized Andean city (Manizales, Colombia). The study also analyzes the effect of using different sets of predictor variables: (1) Spearman coefficients higher than ± 0.3, (2) variables with loadings higher than ± 0.3 from a principal component analysis (PCA), (3) only meteorological variables, and (4) all available variables. In terms of the O3 forecast, the best model was obtained using ANNs with all the available variables as predictors. The methodology could serve other researchers for implementing statistical forecasting models in their regions with limited pollutant information.https://doi.org/10.4209/aaqr.200471Tropospheric ozoneParticulate matterHourly concentrationsAndean citySupport Vector RegressionArtificial Neuronal Network |
| spellingShingle | Felipe Cifuentes Angel Gálvez Carlos M. González Mauricio Orozco-Alzate Beatriz H. Aristizábal Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information Aerosol and Air Quality Research Tropospheric ozone Particulate matter Hourly concentrations Andean city Support Vector Regression Artificial Neuronal Network |
| title | Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information |
| title_full | Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information |
| title_fullStr | Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information |
| title_full_unstemmed | Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information |
| title_short | Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information |
| title_sort | hourly ozone and pm2 5 prediction using meteorological data alternatives for cities with limited pollutant information |
| topic | Tropospheric ozone Particulate matter Hourly concentrations Andean city Support Vector Regression Artificial Neuronal Network |
| url | https://doi.org/10.4209/aaqr.200471 |
| work_keys_str_mv | AT felipecifuentes hourlyozoneandpm25predictionusingmeteorologicaldataalternativesforcitieswithlimitedpollutantinformation AT angelgalvez hourlyozoneandpm25predictionusingmeteorologicaldataalternativesforcitieswithlimitedpollutantinformation AT carlosmgonzalez hourlyozoneandpm25predictionusingmeteorologicaldataalternativesforcitieswithlimitedpollutantinformation AT mauricioorozcoalzate hourlyozoneandpm25predictionusingmeteorologicaldataalternativesforcitieswithlimitedpollutantinformation AT beatrizharistizabal hourlyozoneandpm25predictionusingmeteorologicaldataalternativesforcitieswithlimitedpollutantinformation |