Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM
Accurate and reliable prediction of air pollutant concentrations is important for rational avoidance of air pollution events and government policy responses. However, due to the mobility and dynamics of pollution sources, meteorological conditions, and transformation processes, pollutant concentrati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/21/8863 |
| _version_ | 1797631283273138176 |
|---|---|
| author | Cai Chen Agen Qiu Haoyu Chen Yajun Chen Xu Liu Dong Li |
| author_facet | Cai Chen Agen Qiu Haoyu Chen Yajun Chen Xu Liu Dong Li |
| author_sort | Cai Chen |
| collection | DOAJ |
| description | Accurate and reliable prediction of air pollutant concentrations is important for rational avoidance of air pollution events and government policy responses. However, due to the mobility and dynamics of pollution sources, meteorological conditions, and transformation processes, pollutant concentration predictions are characterized by great uncertainty and instability, making it difficult for existing prediction models to effectively extract spatial and temporal correlations. In this paper, a powerful pollutant prediction model (STA-ResConvLSTM) is proposed to achieve accurate prediction of pollutant concentrations. The model consists of a deep learning network model based on a residual neural network (ResNet), a spatial–temporal attention mechanism, and a convolutional long short-term memory neural network (ConvLSTM). The spatial–temporal attention mechanism is embedded in each residual unit of the ResNet to form a new residual neural network with the spatial–temporal attention mechanism (STA-ResNet). Deep extraction of spatial–temporal distribution features of pollutant concentrations and meteorological data from several cities is carried out using STA-ResNet. Its output is used as an input to the ConvLSTM, which is further analyzed to extract preliminary spatial–temporal distribution features extracted from the STA-ResNet. The model realizes the spatial–temporal correlation of the extracted feature sequences to accurately predict pollutant concentrations in the future. In addition, experimental studies on urban agglomerations around Long Beijing show that the prediction model outperforms various popular baseline models in terms of accuracy and stability. For the single-step prediction task, the proposed pollutant concentration prediction model performs well, exhibiting a root-mean-square error (RMSE) of 9.82. Furthermore, even for the pollutant prediction task of 1 to 48 h, we performed a multi-step prediction and achieved a satisfactory performance, being able to achieve an average RMSE value of 13.49. |
| first_indexed | 2024-03-11T11:21:39Z |
| format | Article |
| id | doaj.art-b4a5455d28984d0ca5c51aa40e607e7a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T11:21:39Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b4a5455d28984d0ca5c51aa40e607e7a2023-11-10T15:12:26ZengMDPI AGSensors1424-82202023-10-012321886310.3390/s23218863Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTMCai Chen0Agen Qiu1Haoyu Chen2Yajun Chen3Xu Liu4Dong Li5School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, ChinaChinese Academy of Surveying and Mapping, Beijing 100830, ChinaJiangsu Provincial Surveying and Mapping Engineering Institute, Nanjing 210013, ChinaChina Electronics Standardization Institute, Beijing 100007, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, ChinaAccurate and reliable prediction of air pollutant concentrations is important for rational avoidance of air pollution events and government policy responses. However, due to the mobility and dynamics of pollution sources, meteorological conditions, and transformation processes, pollutant concentration predictions are characterized by great uncertainty and instability, making it difficult for existing prediction models to effectively extract spatial and temporal correlations. In this paper, a powerful pollutant prediction model (STA-ResConvLSTM) is proposed to achieve accurate prediction of pollutant concentrations. The model consists of a deep learning network model based on a residual neural network (ResNet), a spatial–temporal attention mechanism, and a convolutional long short-term memory neural network (ConvLSTM). The spatial–temporal attention mechanism is embedded in each residual unit of the ResNet to form a new residual neural network with the spatial–temporal attention mechanism (STA-ResNet). Deep extraction of spatial–temporal distribution features of pollutant concentrations and meteorological data from several cities is carried out using STA-ResNet. Its output is used as an input to the ConvLSTM, which is further analyzed to extract preliminary spatial–temporal distribution features extracted from the STA-ResNet. The model realizes the spatial–temporal correlation of the extracted feature sequences to accurately predict pollutant concentrations in the future. In addition, experimental studies on urban agglomerations around Long Beijing show that the prediction model outperforms various popular baseline models in terms of accuracy and stability. For the single-step prediction task, the proposed pollutant concentration prediction model performs well, exhibiting a root-mean-square error (RMSE) of 9.82. Furthermore, even for the pollutant prediction task of 1 to 48 h, we performed a multi-step prediction and achieved a satisfactory performance, being able to achieve an average RMSE value of 13.49.https://www.mdpi.com/1424-8220/23/21/8863pollutant concentrationsresidual networkConvLSTMspatial–temporal attention |
| spellingShingle | Cai Chen Agen Qiu Haoyu Chen Yajun Chen Xu Liu Dong Li Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM Sensors pollutant concentrations residual network ConvLSTM spatial–temporal attention |
| title | Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM |
| title_full | Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM |
| title_fullStr | Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM |
| title_full_unstemmed | Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM |
| title_short | Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM |
| title_sort | prediction of pollutant concentration based on spatial temporal attention resnet and convlstm |
| topic | pollutant concentrations residual network ConvLSTM spatial–temporal attention |
| url | https://www.mdpi.com/1424-8220/23/21/8863 |
| work_keys_str_mv | AT caichen predictionofpollutantconcentrationbasedonspatialtemporalattentionresnetandconvlstm AT agenqiu predictionofpollutantconcentrationbasedonspatialtemporalattentionresnetandconvlstm AT haoyuchen predictionofpollutantconcentrationbasedonspatialtemporalattentionresnetandconvlstm AT yajunchen predictionofpollutantconcentrationbasedonspatialtemporalattentionresnetandconvlstm AT xuliu predictionofpollutantconcentrationbasedonspatialtemporalattentionresnetandconvlstm AT dongli predictionofpollutantconcentrationbasedonspatialtemporalattentionresnetandconvlstm |