A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern China
Having a high-quality historical air pollutant dataset is critical for environmental and epidemiological research. In this study, a novel deep learning model based on convolutional neural network architecture was developed to estimate ground-level ozone concentrations across eastern China. A high-re...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/7/1640 |
| _version_ | 1797437854853365760 |
|---|---|
| author | Sichen Wang Yanfeng Huo Xi Mu Peng Jiang Shangpei Xun Binfang He Wenyu Wu Lin Liu Yonghong Wang |
| author_facet | Sichen Wang Yanfeng Huo Xi Mu Peng Jiang Shangpei Xun Binfang He Wenyu Wu Lin Liu Yonghong Wang |
| author_sort | Sichen Wang |
| collection | DOAJ |
| description | Having a high-quality historical air pollutant dataset is critical for environmental and epidemiological research. In this study, a novel deep learning model based on convolutional neural network architecture was developed to estimate ground-level ozone concentrations across eastern China. A high-resolution maximum daily average 8-h (MDA8) surface ground ozone concentration dataset was generated with the support of the total ozone column from the satellite Tropospheric Monitoring Instrument, meteorological data from the China Meteorological Administration Land Data Assimilation System, and simulations of the WRF-Chem model. The modeled results were compared with in situ measurements in five cities that were not involved in model training, and the mean R<sup>2</sup> of predicted ozone with observed values was 0.9, indicating the good robustness of our model. In addition, we compared the model results with some widely used machine learning techniques (e.g., random forest) and recently published ozone datasets, showing that the accuracy of our model is higher and that the spatial distributions of predicted ozone are more coherent. This study provides an efficient and exact method to estimate ground-level ozone and offers a new perspective for modeling spatiotemporal air pollutants. |
| first_indexed | 2024-03-09T11:28:39Z |
| format | Article |
| id | doaj.art-9d2c8666c0474eae946dd735758775c9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:28:39Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9d2c8666c0474eae946dd735758775c92023-11-30T23:56:52ZengMDPI AGRemote Sensing2072-42922022-03-01147164010.3390/rs14071640A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern ChinaSichen Wang0Yanfeng Huo1Xi Mu2Peng Jiang3Shangpei Xun4Binfang He5Wenyu Wu6Lin Liu7Yonghong Wang8School of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaAnhui Institute of Meteorological Sciences, Key Laboratory for Atmospheric Sciences & Remote Sensing of Anhui Province, Hefei 230031, ChinaSchool of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaSchool of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaAnhui Institute of Meteorological Sciences, Key Laboratory for Atmospheric Sciences & Remote Sensing of Anhui Province, Hefei 230031, ChinaAnhui Institute of Meteorological Sciences, Key Laboratory for Atmospheric Sciences & Remote Sensing of Anhui Province, Hefei 230031, ChinaAnhui Institute of Meteorological Sciences, Key Laboratory for Atmospheric Sciences & Remote Sensing of Anhui Province, Hefei 230031, ChinaState Key Laboratory of Severe Weather (LASW) and Key Laboratory of Atmospheric Chemistry of CMA, Chinese Academy of Meteorological Sciences, Beijing 100081, ChinaResearch Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100029, ChinaHaving a high-quality historical air pollutant dataset is critical for environmental and epidemiological research. In this study, a novel deep learning model based on convolutional neural network architecture was developed to estimate ground-level ozone concentrations across eastern China. A high-resolution maximum daily average 8-h (MDA8) surface ground ozone concentration dataset was generated with the support of the total ozone column from the satellite Tropospheric Monitoring Instrument, meteorological data from the China Meteorological Administration Land Data Assimilation System, and simulations of the WRF-Chem model. The modeled results were compared with in situ measurements in five cities that were not involved in model training, and the mean R<sup>2</sup> of predicted ozone with observed values was 0.9, indicating the good robustness of our model. In addition, we compared the model results with some widely used machine learning techniques (e.g., random forest) and recently published ozone datasets, showing that the accuracy of our model is higher and that the spatial distributions of predicted ozone are more coherent. This study provides an efficient and exact method to estimate ground-level ozone and offers a new perspective for modeling spatiotemporal air pollutants.https://www.mdpi.com/2072-4292/14/7/1640ground-level ozonedeep learningconvolutional neural network |
| spellingShingle | Sichen Wang Yanfeng Huo Xi Mu Peng Jiang Shangpei Xun Binfang He Wenyu Wu Lin Liu Yonghong Wang A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern China Remote Sensing ground-level ozone deep learning convolutional neural network |
| title | A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern China |
| title_full | A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern China |
| title_fullStr | A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern China |
| title_full_unstemmed | A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern China |
| title_short | A High-Performance Convolutional Neural Network for Ground-Level Ozone Estimation in Eastern China |
| title_sort | high performance convolutional neural network for ground level ozone estimation in eastern china |
| topic | ground-level ozone deep learning convolutional neural network |
| url | https://www.mdpi.com/2072-4292/14/7/1640 |
| work_keys_str_mv | AT sichenwang ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT yanfenghuo ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT ximu ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT pengjiang ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT shangpeixun ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT binfanghe ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT wenyuwu ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT linliu ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT yonghongwang ahighperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT sichenwang highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT yanfenghuo highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT ximu highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT pengjiang highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT shangpeixun highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT binfanghe highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT wenyuwu highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT linliu highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina AT yonghongwang highperformanceconvolutionalneuralnetworkforgroundlevelozoneestimationineasternchina |