TFAN: Temporal-Feature correlations Attention-based Network for Urban Air Quality Prediction using Data Fusion technology

Siyuan Ma, Fan Zhang, Wanli Hou, Yarui Li, Wei Song
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:850-865, 2024.

Abstract

Air pollution raises a detrimental impact on human health and natural environment. Accurate prediction of air quality is crucial for effective pollution control and mitigation strategies. Numerous existing methods for analyzing the variation tendency of a specific air component primarily focus on its temporal and spatial information, neglecting the potential interactions between different attributes within the same time interval. In this paper, we propose a Temporal-Feature correlations Attention-based deep learning Network (TFAN), which incorporates data fusion technology. TFAN focuses on capturing temporal dependencies, feature correlations, and the potential relationship between temporal-feature through the Attention mechanism, and the data fusion method allows for a comprehensive consideration of multiple factors on prediction. Experimental results conducted using real-world data from Beijing City demonstrate that TFAN outperforms various baseline models in prediction accuracy for multiple pollutants by 10+%.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-ma24a, title = {{TFAN}: {T}emporal-Feature correlations Attention-based Network for Urban Air Quality Prediction using Data Fusion technology}, author = {Ma, Siyuan and Zhang, Fan and Hou, Wanli and Li, Yarui and Song, Wei}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {850--865}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/ma24a/ma24a.pdf}, url = {https://proceedings.mlr.press/v222/ma24a.html}, abstract = {Air pollution raises a detrimental impact on human health and natural environment. Accurate prediction of air quality is crucial for effective pollution control and mitigation strategies. Numerous existing methods for analyzing the variation tendency of a specific air component primarily focus on its temporal and spatial information, neglecting the potential interactions between different attributes within the same time interval. In this paper, we propose a Temporal-Feature correlations Attention-based deep learning Network (TFAN), which incorporates data fusion technology. TFAN focuses on capturing temporal dependencies, feature correlations, and the potential relationship between temporal-feature through the Attention mechanism, and the data fusion method allows for a comprehensive consideration of multiple factors on prediction. Experimental results conducted using real-world data from Beijing City demonstrate that TFAN outperforms various baseline models in prediction accuracy for multiple pollutants by 10+%.} }
Endnote
%0 Conference Paper %T TFAN: Temporal-Feature correlations Attention-based Network for Urban Air Quality Prediction using Data Fusion technology %A Siyuan Ma %A Fan Zhang %A Wanli Hou %A Yarui Li %A Wei Song %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-ma24a %I PMLR %P 850--865 %U https://proceedings.mlr.press/v222/ma24a.html %V 222 %X Air pollution raises a detrimental impact on human health and natural environment. Accurate prediction of air quality is crucial for effective pollution control and mitigation strategies. Numerous existing methods for analyzing the variation tendency of a specific air component primarily focus on its temporal and spatial information, neglecting the potential interactions between different attributes within the same time interval. In this paper, we propose a Temporal-Feature correlations Attention-based deep learning Network (TFAN), which incorporates data fusion technology. TFAN focuses on capturing temporal dependencies, feature correlations, and the potential relationship between temporal-feature through the Attention mechanism, and the data fusion method allows for a comprehensive consideration of multiple factors on prediction. Experimental results conducted using real-world data from Beijing City demonstrate that TFAN outperforms various baseline models in prediction accuracy for multiple pollutants by 10+%.
APA
Ma, S., Zhang, F., Hou, W., Li, Y. & Song, W.. (2024). TFAN: Temporal-Feature correlations Attention-based Network for Urban Air Quality Prediction using Data Fusion technology. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:850-865 Available from https://proceedings.mlr.press/v222/ma24a.html.

Related Material