Abstract
Accurate forecasting of air pollutant PM2.5(particulate matter with diameter less than 2.5 µm) is beneficial to society. However, the non-linear spatio-temporal correlations, multi-feasible forecast values and incomplete training data due to stochasticity make it challenging for discriminative deep learning approaches to forecasting PM2.5 data. In this paper, a generative modeling approach is proposed to overcome the challenges in forecasting PM2.5 data by considering it as an ill-posed inverse problem. To strengthen its applicability, the proposed approach is theoretically validated. Furthermore, based on the proposed generative modeling, an Autoencoder-based generative adversarial network (GAN) named Air-GAN is developed. Air-GAN combines a convolutional neural network- long short-term memory (CNN-LSTM) based Encoder with a conditional Wasserstein GAN (WGAN) to capture non-linear correlations in the data distribution via inverse mapping from the forecast distribution. The condition vector to conditional WGAN is the novelty in Air-GAN, which employs this inverse learning and allows the WGAN’s Generator to generate accurate forecast estimates from noise distribution. The condition vector is composed of two elements: (1) the category label of the best correlated meteorological parameter with the PM2.5 data, assigned using an efficient classifier and (2) the output of the CNN-LSTM-based Encoder which is the latent representation of the forecast. The extensive evaluation of Air-GAN for predicting the real-time PM2.5 data of Delhi demonstrates its superior performance with an average inference error of 5.3 µg/m3, which achieves 31.7% improvement over the baseline approaches. The improved performance of Air-GAN demonstrates its efficiency to forecast stochastic PM2.5 data by generalizing to out-of-distribution data.
Similar content being viewed by others
Data availability and material
Open-source data.
Code availability
Custom code.
References
Abinaya S, Devi MKK (2021) Enhancing top-N recommendation using stacked autoencoder in context-aware recommender system. Neural Process Lett 53(3):1865–1888. https://doi.org/10.1007/s11063-021-10475-0
Abirami S, Chitra P (2021) Regional air quality forecasting using spatiotemporal deep learning. J Clean Prod 283:125341
Abirami S, Chitra P, Madhumitha R, Kesavan SR (2020) Hybrid spatio-temporal deep learning framework for particulate matter(PM2.5) concentration forecasting. In: 2020 International conference on innovative trends in information technology (ICITIIT), pp. 1–6
Ai Y, Li Z, Gan M et al (2019) A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system. Neural Comput Appl 31:1665–1677. https://doi.org/10.1007/s00521-018-3470-9
Al-Hemoud A, Gasana J, Al-Dabbous A et al (2019) Exposure levels of air pollution (PM2.5) and associated health risk in Kuwait. Environ Res 179:108730
Albawi S, Mohammed TA, Al-Zawi S (2017) Understanding of a convolutional neural network. In: 2017 International conference on engineering and technology (ICET). IEEE, pp 1–6
Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: International conference on machine learning. PMLR, pp 214–223
Beig G, Ghude SD, Deshpande A (2010) Scientific evaluation of air quality standards and defining air quality index for India. CITESEER
Box GEP, Jenkins GM (1968) Some recent advances in forecasting and control. J R Stat Soc Ser C Applied Stat 17:91–109. https://doi.org/10.2307/2985674
Brauer M (2016) The global burden of disease from air pollution. In: 2016 AAAS annual meeting (February 11–15, 2016). AAAS
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Chaudhary V, Deshbhratar A, Kumar V, Paul D (2018) Time series based LSTM model to predict air pollutant’s concentration for prominent cities in India. UDM, Aug
Chen Y, Wang Y, Kirschen D, Zhang B (2018) Model-free renewable scenario generation using generative adversarial networks. IEEE Trans Power Syst 33:3265–3275. https://doi.org/10.1109/TPWRS.2018.2794541
Cheng M, Fang F, Pain CC, Navon IM (2020) Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network. Comput Methods Appl Mech Eng 365:113000
Chitra P, Abirami S (2019) Leveraging fog computing and deep learning for building a secure individual health-based decision support system to evade air pollution. In: Global IGI (ed) Security, privacy, and forensics issues in big data. IGI Global, Amsterdam, pp 380–406
Chitra P, Abirami S (2019) Smart pollution alert system using machine learning. Integrating the internet of things into software engineering practices. IGI Global, Amsterdam, pp 219–235
Donahue J, Krähenbühl P, Darrell T (2016) Adversarial feature learning. arXiv Prepr https://arxiv.org/abs/1605.09782
Du S, Li T, Yang Y, Horng S-J (2019) Deep air quality forecasting using hybrid deep learning framework. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/tkde.2019.2954510
Express Web Desk (2016) Diwali effect: pollution worsens, particulate matter soars in Delhi. In: The Indian Express. http://indianexpress.com/article/india/india-news-india/post-diwali-pm-shoots-up-10-times-more-than-the-safe-limit-3730200/
García Nieto PJ, Combarro EF, del Coz Díaz JJ, Montañés E (2013) A SVM-based regression model to study the air quality at local scale in Oviedo urban area (Northern Spain): a case study. Appl Math Comput 219:8923–8937. https://doi.org/10.1016/j.amc.2013.03.018
Ghaemi Z, Alimohammadi A, Farnaghi M (2018) LaSVM-based big data learning system for dynamic prediction of air pollution in Tehran. Environ Monit Assess. https://doi.org/10.1007/s10661-018-6659-6
Goodfellow IJ, Pouget-Abadie J, Mirza M, et al (2014) Generative adversarial networks. arXiv Prepr https://arxiv.org/abs/1406.2661
Gu K, Qiao J, Lin W (2018) Recurrent air quality predictor based on meteorology-and pollution-related factors. IEEE Trans Ind Inform 14:3946–3955
Gupta P, Christopher SA (2009) Particulate matter air quality assessment using integrated surface, satellite, and meteorological products: Multiple regression approach. J Geophys Res Atmos. https://doi.org/10.1029/2008JD011496
Huang CJ, Kuo PH (2018) A deep cnn-lstm model for particulate matter (PM2.5) forecasting in smart cities. Sensors (Switzerland) 18:2220. https://doi.org/10.3390/s18072220
Huitema B, Laraway S (2006) Autocorrelation
Jaya IGNM, Andriyana Y, Tantular B et al (2019) Spatiotemporal dengue disease clustering by means local spatiotemporal Moran’s index. IOP Conf Ser Mater Sci Eng. https://doi.org/10.1088/1757-899X/621/1/012017
Jiang C, Mao Y, Chai Y, Yu M (2020) Day-ahead renewable scenario forecasts based on generative adversarial networks
Kirch W (2008) Pearson’s correlation coefficient. Encyclopedia of public health. Springer, Netherlands, Dordrecht, pp 1090–1091
Kumar U, Jain VK (2010) ARIMA forecasting of ambient air pollutants (O3, NO, NO2 and CO). Stoch Environ Res Risk Assess 24:751–760. https://doi.org/10.1007/s00477-009-0361-8
Le VD, Cha SK (2018) Real-time air pollution prediction model based on spatiotemporal big data
Lee S, Shin J (2019) Hybrid model of convolutional LSTM and CNN to predict particulate matter. Int J Inf Electron Eng 9:34–38. https://doi.org/10.18178/ijiee.2019.9.1.701
Li C, Hsu NC, Tsay S-C (2011) A study on the potential applications of satellite data in air quality monitoring and forecasting. Atmos Environ 45:3663–3675. https://doi.org/10.1016/j.atmosenv.2011.04.032
Liang D, Kumar N (2013) Time-space Kriging to address the spatiotemporal misalignment in the large datasets. Atmos Environ 72:60–69. https://doi.org/10.1016/j.atmosenv.2013.02.034
Ma X, Dai Z, He Z et al (2017) Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors 17:818
Mahalingam U, Elangovan K, Dobhal H, et al (2019) A machine learning model for air quality prediction for smart cities. In: 2019 International conference on wireless communications signal processing and networking (WiSPNET). pp 452–457
Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv Prepr https://arxiv.org/abs/1411.1784
Mondini A, Chiaravalloti-Neto F (2008) Spatial correlation of incidence of dengue with socioeconomic, demographic and environmental variables in a Brazilian city. Sci Total Environ 393:241–248. https://doi.org/10.1016/j.scitotenv.2008.01.010
Niska H, Hiltunen T, Karppinen A et al (2004) Evolving the neural network model for forecasting air pollution time series. Eng Appl Artif Intell 17:159–167
Pandhe N, Rada B, Quinn S (2018) Generative spatiotemporal modeling of neutrophil behavior. In: Proc—Int symp biomed imaging 2018: 969–972. https://doi.org/10.1109/ISBI.2018.8363732
Panwar S, Rad P, Jung T-P, Huang Y (2019) Modeling EEG data distribution with a Wasserstein generative adversarial network to predict RSVP events
Pearce JL, Rathbun SL, Aguilar-Villalobos M, Naeher LP (2009) Characterizing the spatiotemporal variability of PM2.5 in Cusco, Peru using kriging with external drift. Atmos Environ 43:2060–2069. https://doi.org/10.1016/j.atmosenv.2008.10.060
Qin S, Liu F, Wang C et al (2015) Spatial-temporal analysis and projection of extreme particulate matter (PM10 and PM2.5) levels using association rules: a case study of the Jing-Jin-Ji region, China. Atmos Environ 120:339–350. https://doi.org/10.1016/j.atmosenv.2015.09.006
Rokach L, Maimon O (2005) Clustering methods. Data mining and knowledge discovery handbook. Springer, New York, pp 321–352
Shad R, Mesgari MS, Shad A (2009) Predicting air pollution using fuzzy genetic linear membership kriging in GIS. Comput Environ Urban Syst 33:472–481
Sharma M, Jain S, Mittal S, Sheikh TH (2021) Forecasting and prediction of air pollutants concentrates using machine learning techniques the case of India. IOP Conf Series: Mater Sci Eng 1022:12123
Sivasundaram S, Pandian C (2021) Performance analysis of classification and segmentation of cysts in panoramic dental images using convolutional neural network architecture. Int J Imaging Syst Technol 31(4):2214–2225. https://doi.org/10.1002/ima.22625
Tan Z, Gao M, Li X, Jiang L (2021) A flexible reference-insensitive spatiotemporal fusion model for remote sensing images using conditional generative adversarial network. IEEE Trans Geosci Remote Sens 60:1–13
Tieu N-DT, Nguyen HH, Nguyen-Son H-Q et al (2019) Spatio-temporal generative adversarial network for gait anonymization. J Inf Secur Appl 46:307–319
WHO News Release (2018) 9 out of 10 people worldwide breathe polluted air, but more countries are taking action. In: World Heal. Organ. https://www.who.int/news/item/02-05-2018-9-out-of-10-people-worldwide-breathe-polluted-air-but-more-countries-are-taking-action
Yu H, Chen X, Li Z et al (2019) Taxi-based mobility demand formulation and prediction using conditional generative adversarial network-driven learning approaches. IEEE Trans Intell Transp Syst 20:3888–3899. https://doi.org/10.1109/TITS.2019.2923964
Yu H, Li Z, Zhang G et al (2020) Extracting and predicting taxi hotspots in spatiotemporal dimensions using conditional generative adversarial neural networks. IEEE Trans Veh Technol 69:3680–3692. https://doi.org/10.1109/TVT.2020.2978450
Zhang H, Song Y, Han C, Zhang L (2020) Remote sensing image spatiotemporal fusion using a generative adversarial network. IEEE Trans Geosci Remote Sens 59:4273–4286
Zhang Y (2012) Support vector machine classification algorithm and its application. International conference on information computing and applications. Springer, Berlin, pp 179–186
Zhang Y, Wang S, Chen B et al (2019) TrafficGAN: network-scale deep traffic prediction with generative adversarial nets. IEEE Trans Intell Transp Syst 230:219–230. https://doi.org/10.1109/tits.2019.2955794
Zhu D, Cai C, Yang T, Zhou X (2018) A machine learning approach for air quality prediction: model regularization and optimization. Big Data Cogn Comput 2:5. https://doi.org/10.3390/bdcc2010005
Zhu Q, Chen J, Shi D et al (2020) Learning temporal and spatial correlations jointly: a unified framework for wind speed prediction. IEEE Trans Sustain Energy 11:509–523. https://doi.org/10.1109/TSTE.2019.2897136
Acknowledgements
Authors are thankful to the All-India Council for Technical Education (AICTE)-NDF Scheme for providing a research fellowship to support this research.
Funding
None.
Author information
Authors and Affiliations
Contributions
SA Conceptualization, methodology, software, original draft preparation; PC: supervision, writing- reviewing and editing. Acknowledgements- Authors are thankful to the All-India Council for Technical Education (AICTE)-NDF Scheme for providing a research fellowship to support this research.
Corresponding authors
Ethics declarations
Conflict of interest
None.
Consent to participate
Yes.
Consent for publication
Yes.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Abirami, S., Chitra, P. Regional spatio-temporal forecasting of particulate matter using autoencoder based generative adversarial network. Stoch Environ Res Risk Assess 36, 1255–1276 (2022). https://doi.org/10.1007/s00477-021-02153-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-021-02153-3