Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-Validations
A precise air pollution forecast is the basis for targeted pollution control and sustained improvements in air quality. It is desirable and crucial to select the most suitable model for air pollution forecasting (APF). To achieve this goal, this paper provides a comprehensive evaluation of performan...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/13/10/1527 |
| _version_ | 1797475423787941888 |
|---|---|
| author | Zhi Qiao Shengcheng Cui Chenglei Pei Zhou Ye Xiaoqing Wu Lei Lei Tao Luo Zihan Zhang Xuebin Li Wenyue Zhu |
| author_facet | Zhi Qiao Shengcheng Cui Chenglei Pei Zhou Ye Xiaoqing Wu Lei Lei Tao Luo Zihan Zhang Xuebin Li Wenyue Zhu |
| author_sort | Zhi Qiao |
| collection | DOAJ |
| description | A precise air pollution forecast is the basis for targeted pollution control and sustained improvements in air quality. It is desirable and crucial to select the most suitable model for air pollution forecasting (APF). To achieve this goal, this paper provides a comprehensive evaluation of performances of different models in simulating the most common air pollutants (e.g., PM<sub>2.5</sub>, NO<sub>2</sub>, SO<sub>2</sub>, and CO) in Guangzhou (23.13° N, 113.26° E), China. To simulate temporal variations of the above-mentioned air pollutant concentrations in Guangzhou in September and October 2020, we use a numerical forecasting model (i.e., the Weather Research and Forecasting model with Chemistry (WRF-Chem)) and two artificial intelligence models (i.e., the back propagation neural network (BPNN) model and the long short-term memory (LSTM) model). WRF-Chem is also used to simulate the meteorological elements (e.g., the 2 m temperature (T2), 2 m relative humidity (RH), and 10 m wind speed and direction (WS, WD)). In order to investigate the simulation accuracies of classical APF models, we simultaneously compare the simulations of the WRF-Chem, BPNN, and LSTM models to ground truth observations. Comparative assessment results show that WRF-Chem simulated air pollutant (i.e., PM<sub>2.5</sub>, NO<sub>2</sub>, SO<sub>2</sub>, and CO) concentrations have the best correlations with ground measurements (i.e., Pearson correlation coefficient R = 0.88, 0.73, 0.61, and 0.61, respectively). Furthermore, to evaluate model performance in terms of accuracy and stability, the normalized mean bias (NMB, %) and mean fractional bias (MFB, %) are adopted as the standard performance metrics (SPMs) proposed by Boylan et al. The comparison results indicate that when simulating PM<sub>2.5</sub>, WRF-Chem was more effective than the BPNN but less effective than the LSTM. While simulating concentrations of NO<sub>2</sub>, SO<sub>2</sub>, and CO, the WRF-Chem model performed better than the BPNN and LSTM models. With regards to WRF-Chem, the NMBs and MFBs for the PM<sub>2.5</sub> simulations are, respectively, 6.49% and 0.02%, –11.96% and –0.031% for NO<sub>2</sub>, 7.93% and 0.019% for CO, and 5.04% and 0.012% for SO<sub>2</sub>. Our results suggest that WRF-Chem has superior performance and better accuracy than the NN-based prediction models, making it a promising and useful tool to accurately predict and forecast regional air pollutant concentrations on a city scale. |
| first_indexed | 2024-03-09T20:44:53Z |
| format | Article |
| id | doaj.art-9a8ef738fe814d9184dbe785d192ec44 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-09T20:44:53Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-9a8ef738fe814d9184dbe785d192ec442023-11-23T22:49:38ZengMDPI AGAtmosphere2073-44332022-09-011310152710.3390/atmos13101527Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-ValidationsZhi Qiao0Shengcheng Cui1Chenglei Pei2Zhou Ye3Xiaoqing Wu4Lei Lei5Tao Luo6Zihan Zhang7Xuebin Li8Wenyue Zhu9Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaState Key Laboratory of Organic Geochemistry and Guangdong Key Laboratory of Environmental Protection and Resources Utilization, Guangzhou Institute of Geochemistry, Chinese Academy of Sciences, Guangzhou 510640, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaGuangzhou Sub-Branch of Guangdong Ecological and Environmental Monitoring Center, Guangzhou 510060, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, ChinaA precise air pollution forecast is the basis for targeted pollution control and sustained improvements in air quality. It is desirable and crucial to select the most suitable model for air pollution forecasting (APF). To achieve this goal, this paper provides a comprehensive evaluation of performances of different models in simulating the most common air pollutants (e.g., PM<sub>2.5</sub>, NO<sub>2</sub>, SO<sub>2</sub>, and CO) in Guangzhou (23.13° N, 113.26° E), China. To simulate temporal variations of the above-mentioned air pollutant concentrations in Guangzhou in September and October 2020, we use a numerical forecasting model (i.e., the Weather Research and Forecasting model with Chemistry (WRF-Chem)) and two artificial intelligence models (i.e., the back propagation neural network (BPNN) model and the long short-term memory (LSTM) model). WRF-Chem is also used to simulate the meteorological elements (e.g., the 2 m temperature (T2), 2 m relative humidity (RH), and 10 m wind speed and direction (WS, WD)). In order to investigate the simulation accuracies of classical APF models, we simultaneously compare the simulations of the WRF-Chem, BPNN, and LSTM models to ground truth observations. Comparative assessment results show that WRF-Chem simulated air pollutant (i.e., PM<sub>2.5</sub>, NO<sub>2</sub>, SO<sub>2</sub>, and CO) concentrations have the best correlations with ground measurements (i.e., Pearson correlation coefficient R = 0.88, 0.73, 0.61, and 0.61, respectively). Furthermore, to evaluate model performance in terms of accuracy and stability, the normalized mean bias (NMB, %) and mean fractional bias (MFB, %) are adopted as the standard performance metrics (SPMs) proposed by Boylan et al. The comparison results indicate that when simulating PM<sub>2.5</sub>, WRF-Chem was more effective than the BPNN but less effective than the LSTM. While simulating concentrations of NO<sub>2</sub>, SO<sub>2</sub>, and CO, the WRF-Chem model performed better than the BPNN and LSTM models. With regards to WRF-Chem, the NMBs and MFBs for the PM<sub>2.5</sub> simulations are, respectively, 6.49% and 0.02%, –11.96% and –0.031% for NO<sub>2</sub>, 7.93% and 0.019% for CO, and 5.04% and 0.012% for SO<sub>2</sub>. Our results suggest that WRF-Chem has superior performance and better accuracy than the NN-based prediction models, making it a promising and useful tool to accurately predict and forecast regional air pollutant concentrations on a city scale.https://www.mdpi.com/2073-4433/13/10/1527WRF-Chemback propagation neural networklong short-term memoryair pollutionGuangzhou |
| spellingShingle | Zhi Qiao Shengcheng Cui Chenglei Pei Zhou Ye Xiaoqing Wu Lei Lei Tao Luo Zihan Zhang Xuebin Li Wenyue Zhu Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-Validations Atmosphere WRF-Chem back propagation neural network long short-term memory air pollution Guangzhou |
| title | Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-Validations |
| title_full | Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-Validations |
| title_fullStr | Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-Validations |
| title_full_unstemmed | Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-Validations |
| title_short | Regional Predictions of Air Pollution in Guangzhou: Preliminary Results and Multi-Model Cross-Validations |
| title_sort | regional predictions of air pollution in guangzhou preliminary results and multi model cross validations |
| topic | WRF-Chem back propagation neural network long short-term memory air pollution Guangzhou |
| url | https://www.mdpi.com/2073-4433/13/10/1527 |
| work_keys_str_mv | AT zhiqiao regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT shengchengcui regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT chengleipei regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT zhouye regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT xiaoqingwu regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT leilei regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT taoluo regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT zihanzhang regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT xuebinli regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations AT wenyuezhu regionalpredictionsofairpollutioninguangzhoupreliminaryresultsandmultimodelcrossvalidations |