Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural Network
With the development of industrialization and the increase in the number of motor vehicles in megacities in China, ozone pollution has become a prominent problem. Although different models have been used on ozone concentration simulation, the accuracy of different models still varies. In this study,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/13/9/1371 |
| _version_ | 1797491351191814144 |
|---|---|
| author | Jie Yu Lingxuan Xu Shuang Gao Li Chen Yanling Sun Jian Mao Hui Zhang |
| author_facet | Jie Yu Lingxuan Xu Shuang Gao Li Chen Yanling Sun Jian Mao Hui Zhang |
| author_sort | Jie Yu |
| collection | DOAJ |
| description | With the development of industrialization and the increase in the number of motor vehicles in megacities in China, ozone pollution has become a prominent problem. Although different models have been used on ozone concentration simulation, the accuracy of different models still varies. In this study, the performance of two models including a linear stepwise regression (SR) model and a non-linear artificial neural network (ANN) model on the simulation of ozone concentration were analyzed in the Jing-Jin-Ji region, which is one of the most polluted areas in China. Results showed that the performance of the ANN model (adjusted R<sup>2</sup> = 0.8299, RMSE = 22.87, MAE = 16.92) was better than the SR model (adjusted R<sup>2</sup> = 0.7324, RMSE = 28.61, MAE = 22.30). The performance of the ANN on simulating an ozone pollution event was better than the SR model since a higher probability of detection (POD) and threat score (TS) values were obtained by the ANN model. The model performance for spring, autumn and winter was generally higher than that for summer, which may because the weights of factors on simulating high and low ozone concentrations were different. The method proposed by this study can be used in ozone concentration estimation. |
| first_indexed | 2024-03-10T00:47:09Z |
| format | Article |
| id | doaj.art-865e4be183944f0b8bb1e5922bc8d95b |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T00:47:09Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-865e4be183944f0b8bb1e5922bc8d95b2023-11-23T14:58:30ZengMDPI AGAtmosphere2073-44332022-08-01139137110.3390/atmos13091371Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural NetworkJie Yu0Lingxuan Xu1Shuang Gao2Li Chen3Yanling Sun4Jian Mao5Hui Zhang6School of Geographic and Environmental Sciences, Tianjin Normal University, Tianjin 300387, ChinaSchool of Geographic and Environmental Sciences, Tianjin Normal University, Tianjin 300387, ChinaSchool of Geographic and Environmental Sciences, Tianjin Normal University, Tianjin 300387, ChinaSchool of Geographic and Environmental Sciences, Tianjin Normal University, Tianjin 300387, ChinaSchool of Geographic and Environmental Sciences, Tianjin Normal University, Tianjin 300387, ChinaSchool of Geographic and Environmental Sciences, Tianjin Normal University, Tianjin 300387, ChinaSchool of Geographic and Environmental Sciences, Tianjin Normal University, Tianjin 300387, ChinaWith the development of industrialization and the increase in the number of motor vehicles in megacities in China, ozone pollution has become a prominent problem. Although different models have been used on ozone concentration simulation, the accuracy of different models still varies. In this study, the performance of two models including a linear stepwise regression (SR) model and a non-linear artificial neural network (ANN) model on the simulation of ozone concentration were analyzed in the Jing-Jin-Ji region, which is one of the most polluted areas in China. Results showed that the performance of the ANN model (adjusted R<sup>2</sup> = 0.8299, RMSE = 22.87, MAE = 16.92) was better than the SR model (adjusted R<sup>2</sup> = 0.7324, RMSE = 28.61, MAE = 22.30). The performance of the ANN on simulating an ozone pollution event was better than the SR model since a higher probability of detection (POD) and threat score (TS) values were obtained by the ANN model. The model performance for spring, autumn and winter was generally higher than that for summer, which may because the weights of factors on simulating high and low ozone concentrations were different. The method proposed by this study can be used in ozone concentration estimation.https://www.mdpi.com/2073-4433/13/9/1371ozoneartificial neural networkstepwise regression model |
| spellingShingle | Jie Yu Lingxuan Xu Shuang Gao Li Chen Yanling Sun Jian Mao Hui Zhang Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural Network Atmosphere ozone artificial neural network stepwise regression model |
| title | Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural Network |
| title_full | Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural Network |
| title_fullStr | Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural Network |
| title_full_unstemmed | Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural Network |
| title_short | Establishment of a Combined Model for Ozone Concentration Simulation with Stepwise Regression Analysis and Artificial Neural Network |
| title_sort | establishment of a combined model for ozone concentration simulation with stepwise regression analysis and artificial neural network |
| topic | ozone artificial neural network stepwise regression model |
| url | https://www.mdpi.com/2073-4433/13/9/1371 |
| work_keys_str_mv | AT jieyu establishmentofacombinedmodelforozoneconcentrationsimulationwithstepwiseregressionanalysisandartificialneuralnetwork AT lingxuanxu establishmentofacombinedmodelforozoneconcentrationsimulationwithstepwiseregressionanalysisandartificialneuralnetwork AT shuanggao establishmentofacombinedmodelforozoneconcentrationsimulationwithstepwiseregressionanalysisandartificialneuralnetwork AT lichen establishmentofacombinedmodelforozoneconcentrationsimulationwithstepwiseregressionanalysisandartificialneuralnetwork AT yanlingsun establishmentofacombinedmodelforozoneconcentrationsimulationwithstepwiseregressionanalysisandartificialneuralnetwork AT jianmao establishmentofacombinedmodelforozoneconcentrationsimulationwithstepwiseregressionanalysisandartificialneuralnetwork AT huizhang establishmentofacombinedmodelforozoneconcentrationsimulationwithstepwiseregressionanalysisandartificialneuralnetwork |