Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM
Sensors · 31.10.2023 · 23 (21) · 8863
DOI: 10.3390/s23218863 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 31.10.2023. Verfasst von Cai Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAMS NIH HHS, State Key Laboratory of Geo-Information Engineering, Chinese Academy of Surveying and Mapping Basic Research Fund Program.
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, China.
- Chinese Academy of Surveying and Mapping, Beijing 100830, China.
- Jiangsu Provincial Surveying and Mapping Engineering Institute, Nanjing 210013, China.
- China Electronics Standardization Institute, Beijing 100007, China.
Förderung
- NIAMS NIH HHS
- State Key Laboratory of Geo-Information Engineering
- Chinese Academy of Surveying and Mapping Basic Research Fund Program
Zitieren
APA
Chen, C., Qiu, A., Chen, H., Chen, Y., Liu, X., & Li, D. (2023). Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM. Sensors, 23(21), 8863. https://doi.org/10.3390/s23218863
Vancouver
Chen C, Qiu A, Chen H, Chen Y, Liu X, Li D. Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM. Sensors. 2023;23(21):8863. doi:10.3390/s23218863
BibTeX
@article{Chen2023,
author = {Chen, Cai and Qiu, Agen and Chen, Haoyu and Chen, Yajun and Liu, Xu and Li, Dong},
title = {Prediction of Pollutant Concentration Based on Spatial–Temporal Attention, ResNet and ConvLSTM},
journal = {Sensors},
year = {2023},
volume = {23},
number = {21},
pages = {8863},
doi = {10.3390/s23218863}
}
EUVIMED