Nationwide Air Pollution Forecasting with Heterogeneous Graph Neural Networks
Article No.: 18, Pages 1 - 19
Abstract
Nowadays, air pollution is one of the most relevant environmental problems in most urban settings. Due to the utility in operational terms of anticipating certain pollution levels, several predictors based on Graph Neural Networks (GNN) have been proposed for the last years. Most of these solutions usually encode the relationships among stations in terms of their spatial distance, but they fail when it comes to capturing other spatial and feature-based contextual factors. Besides, they assume a homogeneous setting where all the stations are able to capture the same pollutants. However, large-scale settings frequently comprise different types of stations, each one with different measurement capabilities. For that reason, the present article introduces a novel GNN framework able to capture the similarities among stations related to the land use of their locations and their primary source of pollution. Furthermore, we define a methodology to deal with heterogeneous settings on the top of the GNN architecture. Finally, the proposal has been tested with a nation-wide Spanish air-pollution dataset with very promising results.
References
[1]
Eurostat. 2022. Passenger Mobility Statistics. Technical Report.
[2]
Patricia Arroyo, José Luis Herrero, José Ignacio Suárez, and Jesús Lozano. 2019. Wireless sensor network combined with cloud computing for air quality monitoring. Sensors 19, 3 (2019), 691.
[3]
Zena A. Aziz Aziz and Siddeeq Y. Ameen Ameen. 2021. Air pollution monitoring using wireless sensor networks. J. Inf. Technol. Inform. 1, 1 (2021), 20–25.
[4]
Kevin Cromar and Noussair Lazrak. 2023. Risk communication of ambient air pollution in the WHO European Region: Review of air quality indexes and lessons learned. World Health Organization, (2023).
[5]
Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Adv. Neural Inf. Process. Syst. 29 (2016).
[6]
Zhenni Ding, Huayou Chen, Ligang Zhou, and Zicheng Wang. 2022. A forecasting system for deterministic and uncertain prediction of air pollution data. Expert Syst. Applic. 208 (2022), 118123.
[7]
Ao Dun, Yuning Yang, and Fei Lei. 2022. Dynamic graph convolution neural network based on spatial-temporal correlation for air quality prediction. Ecolog. Inform. 70 (2022), 101736.
[8]
Shaohua Fan, Junxiong Zhu, Xiaotian Han, Chuan Shi, Linmei Hu, Biyu Ma, and Yongliang Li. 2019. Metapath-guided heterogeneous graph neural network for intent recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2478–2486.
[9]
Aysenur Gilik, Arif Selcuk Ogrenci, and Atilla Ozmen. 2022. Air quality prediction using CNN+ LSTM-based hybrid deep learning architecture. Environ. Sci. Pollut. Res. 29, 8 (2022), 1–19.
[10]
Jindong Han, Hao Liu, Haoyi Xiong, and Jing Yang. 2022. Semi-supervised air quality forecasting via self-supervised hierarchical graph neural network. IEEE Trans. Knowl. Data Eng. 35, 5 (2022).
[11]
Azim Heydari, Meysam Majidi Nezhad, Davide Astiaso Garcia, Farshid Keynia, and Livio De Santoli. 2021. Air pollution forecasting application based on deep learning model and optimization algorithm. Clean Technol. Environ. Polic. 24, 2 (2021), 1–15.
[12]
Rosaria Ignaccolo, Stefania Ghigo, and Stefano Bande. 2013. Functional zoning for air quality. Environ. Ecolog. Stat. 20 (2013), 109–127.
[13]
Ditsuhi Iskandaryan, Francisco Ramos, and Sergio Trilles. 2023. Graph neural network for air quality prediction: A case study in Madrid. IEEE Access 11 (2023), 2729–2742.
[14]
Xue-Bo Jin, Zhong-Yao Wang, Jian-Lei Kong, Yu-Ting Bai, Ting-Li Su, Hui-Jun Ma, and Prasun Chakrabarti. 2023. Deep spatio-temporal graph network with self-optimization for air quality prediction. Entropy 25, 2 (2023), 247.
[15]
Gamze Kurnaz and Alparslan Serhat Demir. 2022. Prediction of SO2 and PM10 air pollutants using a deep learning-based recurrent neural network: Case of industrial city Sakarya. Urb. Clim. 41 (2022), 101051.
[16]
Zewen Li, Fan Liu, Wenjie Yang, Shouheng Peng, and Jun Zhou. 2021. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst. 33, 12 (2021).
[17]
Nilesh N. Maltare and Safvan Vahora. 2023. Air quality index prediction using machine learning for Ahmedabad City. Digit. Chem. Eng. 7 (2023), 100093.
[18]
Concettina Marino, Antonino Nucara, Maria Francesca Panzera, and Matilde Pietrafesa. 2022. Assessment of the road traffic air pollution in urban contexts: A statistical approach. Sustainability 14, 7 (2022), 4127.
[19]
Harvey J. Miller. 2004. Tobler’s first law and spatial analysis. Ann. Assoc. Am. Geogr. 94, 2 (2004), 284–289.
[20]
Movilidad y Agenda Urbana Secretaría de Estado de Transportes. 2020. Análisis de la movilidad en España con tecnología Big Data durante el estado de alarma para la gestión de la crisis del COVID-19. Technical Report. Ministerio de Transportes, Movilidad y Agenda Urbana.
[21]
Youngjoo Seo, Michaël Defferrard, Pierre Vandergheynst, and Xavier Bresson. 2018. Structured sequence modeling with graph convolutional recurrent networks. In 25th International Conference on Neural Information Processing (ICONIP’18). Springer, 362–373.
[22]
Greg Van Houdt, Carlos Mosquera, and Gonzalo Nápoles. 2020. A review on the long short-term memory model. Artif. Intell. Rev. 53 (2020), 5929–5955.
[23]
Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. stat 1050, 20 (2017), 10–48550.
[24]
Xiao Wang, Deyu Bo, Chuan Shi, Shaohua Fan, Yanfang Ye, and S. Yu Philip. 2022. A survey on heterogeneous graph embedding: Methods, techniques, applications and sources. IEEE Trans. Big Data 9, 2 (2022), 415–436.
[25]
C. J. Willmott and K. Matsuura. 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30, 1 (2005), 79–82.
[26]
Carlos Zafra, Yenifer Ángel, and Eliana Torres. 2017. ARIMA analysis of the effect of land surface coverage on PM10 concentrations in a high-altitude megacity. Atmos. Pollut. Res. 8, 4 (2017), 660–668.
[27]
Nur’atiah Zaini, Lee Woen Ean, Ali Najah Ahmed, and Marlinda Abdul Malek. 2022. A systematic literature review of deep learning neural network for time series air quality forecasting. Environ. Sci. Pollut. Res. 29, 4 (2022), 1–33.
[28]
Shuang Zhao, Shiliang Liu, Xiaoyun Hou, Yongxiu Sun, and Robert Beazley. 2021. Air pollution and cause-specific mortality: A comparative study of urban and rural areas in China. Chemosphere 262 (2021), 127884.
Index Terms
- Nationwide Air Pollution Forecasting with Heterogeneous Graph Neural Networks
Recommendations
A review of artificial neural network models for ambient air pollution prediction
AbstractResearch activity in the field of air pollution forecasting using artificial neural networks (ANNs) has increased dramatically in recent years. However, the development of ANN models entails levels of uncertainty given the black-box ...
Highlights- Research activity in ambient air pollution forecasting with ANNs continues to grow .
Air pollution in the area around the mining complex Trepça in Kosovo
EE'10: Proceedings of the 5th IASME/WSEAS international conference on Energy & environmentIn this paper are presented the results of air pollution in Mining Complex Trepça in Kosovo. The region is significantly affected by industrial pollution which is affected by the mining sector. Associated to the region there is effluents by toxic/acidic ...
Forecasting air pollution load in Delhi using data analysis tools
AbstractThe enormity of air pollution has always been a matter of concern due to rapid development and urbanization over a long period. The increasing level of pollutants in ambient air in 2016-2017 has deteriorated the air quality of Delhi at an alarming ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 16 January 2024
Online AM: 14 December 2023
Accepted: 10 December 2023
Revised: 26 October 2023
Received: 26 May 2023
Published in TIST Volume 15, Issue 1
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- “EMERGIA” programme
- Junta de Andalucía
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 329Total Downloads
- Downloads (Last 12 months)329
- Downloads (Last 6 weeks)59
Reflects downloads up to 17 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in