PM2.5 concentration prediction using Generative adversarial network: A novel approach
##plugins.themes.bootstrap3.article.main##
Abstract
Over the last few years, air pollution has become a matter of great concern. Numerous machine learning and deep learning techniques have been applied to predict PM2.5 (Particulate Matter2.5). However, deterministic models perform forecasting based on the mean of probable outputs and cannot handle the uncertainties in real-life situations. With the aim of solving the low accuracy of PM2.5 concentration prediction during uncertainties, the present study proposed an innovative probabilistic model-Prob PM2.5 which predicts one day ahead PM2.5 concentration for time series data, which is multivariate in nature. First, a comprehensive correlation analysis between the meteorological features and PM2.5 concentration is done. Finally, the Conditional GAN framework is used to train the ProbPM2.5 with the help of adversarial training. The proposed framework that transformed a deterministic model into a probabilistic model provided improved performance. Comparative analysis with conventional models, such as LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit) reveals that ProbPM2.5 outperforms during testing, showcasing resilience in the face of unforeseen events like COVID-19. Hence, the proposed method could perform improved characterization of time series characteristics of the air pollutant changes in order to obtain better accuracy of PM2.5 concentration prediction
##plugins.themes.bootstrap3.article.details##
##plugins.themes.bootstrap3.article.details##
Keywords
Air pollution monitoring, Gated Recurrent Unit, Generative adversarial network, Long-short term memory, Multivariate time series data, PM2.5 prediction
References
Amnuaylojaroen, T. & Parasin, N. (2023). Future health risk assessment of exposure to PM2.5 in different age groups of children in Northern Thailand. Toxics, 11(3), 291.
Bai, T., Luo, J., Zhao, J., Wen, B. & Wang, Q. (2021). Recent advances in adversarial training for adversarial robustness. arXiv Preprint arXiv:2102.01356.
Barman, N. & Gokhale, S. (2019). Urban black carbon-source apportionment, emissions and long-range transport over the Brahmaputra River Valley. Science of the Total Environment, 693, 133577.
Berrisch, J. & Ziel, F. (2023). CRPS Learning. Journal of Econometrics, 237(2), 105221. https://doi.org/10.1016/j.jeconom.2021.11.008
Bhadauria, N., Chauhan, A., Ranjan, R. & Jindal, T. (2023). An assessment of seasonal, monthly and diurnal variations of ambient air quality in the Gurugram city (Haryana). Journal of Applied and Natural Science, 15(1), Article 1. https://doi.org/10.31018/jans.v15i1.4142
Biswas, J. & Pathak, B. (2022). Effects of COVID-19 pandemic lockdown: A satellite data-based appraisal of air quality in Guwahati, Assam. Materials Today: Proceedings, 65, 2794–2800. https://doi.org/10.1016/j.matpr.2022.06.218
Chai, T. & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE). Geoscientific Model Development Discussions, 7(1), 1525–1534.
CPCB (2024). Central Pollution Control Board (CPCB). (n.d.). Retrieved January 2, 2024, from https://cpcb.nic.in/
Dutta, A., Jinsart, W., Das, U. C. & Dutta, G. (2023). An empirical analysis of Delhi’s air quality throughout different COVID-19 pandemic waves. Journal of Applied and Natural Science, 15(1), Article 1. https://doi.org/10.31018/jans.v15i1.4271
Evans, J., van Donkelaar, A., Martin, R. V., Burnett, R., Rainham, D. G., Birkett, N. J. & Krewski, D. (2013). Estimates of global mortality attributable to particulate air pollution using satellite imagery. Environmental Research, 120, 33–42.
Feng, S., Gao, D., Liao, F., Zhou, F. & Wang, X. (2016). The health effects of ambient PM2.5 and potential mechanisms. Ecotoxicology and Environmental Safety, 128, 67–74. https://doi.org/10.1016/j.ecoenv.2016.01.030
Gneiting, T. & Katzfuss, M. (2014). Probabilistic forecasting. Annual Review of Statistics and Its Application, 1, 125–151.
Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep learning. MIT press.
Hany, J. & Walters, G. (2019). Hands-On Generative Adversarial Networks with PyTorch 1. x: Implement next-generation neural networks to build powerful GAN models using Python. Packt Publishing Ltd. https://books.google.com/books?hl=en&lr=&id=URbEDwAAQBAJ&oi=fnd&pg=PP1&dq=select+optimal+discriminator+in+gan+using+pytorch&ots=WgywmebEz3&sig=Ci7g85UESAxhJ0lpwO_kRTPyUxk
Hersbach, H. (2000). Decomposition of the Continuous Ranked Probability Score for Ensemble Prediction Systems. Weather and Forecasting - WEATHER FORECAST, 15, 559–570. https://doi.org/10.1175/1520-0434(2000)015<0559:DOTCRP>2.0.CO;2
Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
Khanna, D. R., Nigam, N. S. & Bhutiani, R. (2013). Monitoring of ambient air quality in relation to traffic density in Bareilly City (U.P.), India. Journal of Applied and Natural Science, 5(2), Article 2. https://doi.org/10.31018/jans.v5i2.359
Kim, B., Kim, E., Jung, S., Kim, M., Kim, J. & Kim, S. (2023). PM2.5 Concentration Forecasting Using Weighted Bi-LSTM and Random Forest Feature Importance-Based Feature Selection. Atmosphere, 14, 968. https://doi.org/10.3390/atmos14060968
Kioumourtzoglou, M.-A., Schwartz, J. D., Weisskopf, M. G., Melly, S. J., Wang, Y., Dominici, F. & Zanobetti, A. (2016). Long-term PM2. 5 exposure and neurological hospital admissions in the northeastern United States. Environmental Health Perspectives, 124(1), 23–29.
Liu, A., Liu, X., Fan, J., Ma, Y., Zhang, A., Xie, H. & Tao, D. (2019). Perceptual-sensitive gan for generating adversarial patches. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 1028–1035. https://ojs.aaai.org/index.php/AAAI/article/view/3893
Liu, Y., Shi, G., Zhan, Y., Zhou, L. & Yang, F. (2021). Characteristics of PM2. 5 spatial distribution and influencing meteorological conditions in Sichuan Basin, southwestern China. Atmospheric Environment, 253, 118364.
Mahalakshmi, G., Sridevi, S. & Rajaram, S. (2016). A survey on forecasting of time series data. 2016 International Conference on Computing Technologies and Intelligent Data Engineering (ICCTIDE’16), 1–8.
Mangayarkarasi, R., Vanmathi, C., Khan, M. Z., Noorwali, A., Jain, R. & Agarwal, P. (2021). COVID19: Forecasting Air Quality Index and Particulate Matter (PM2. 5). Computers, Materials & Continua, 67(3). https://research.vit.ac.in/publication/covid19-forecasting-air-quality-index-and-particulate-matter-pm25/pdf/publisher-pdf-fulltext-covid19-forecasting-air-quality-index-and-particulate-matter-pm25.pdf
Medhi, S. & Gogoi, M. (2021). Visualization and Analysis of COVID-19 Impact on PM2. 5 Concentration in Guwahati city. 2021 International Conference on Computational Performance Evaluation (ComPE), 012–016.
Muruganandam, N. S. & Arumugam, U. (2023). Dynamic Ensemble Multivariate Time Series Forecasting Model for PM2. 5. Computer Systems Science & Engineering, 44(2). https://cdn.techscience.cn/ueditor/files/csse/TSP_ CSSE-44-2/TSP_CSSE_24943/TSP_CS SE_24943.pdf
O’Donnell, M. J., Fang, J., Mittleman, M. A., Kapral, M. K. & Wellenius, G. A. (2011). Fine Particulate Air Pollution (PM2.5) and the Risk of Acute Ischemic Stroke. Epidemiology (Cambridge, Mass.), 22(3), 422–431. https://doi.org/10.1097/EDE.0b013e3182126580
Oliveira, M., Slezakova, K., Delerue-Matos, C., Pereira, M. C. & Morais, S. (2016). Assessment of air quality in preschool environments (3–5 years old children) with emphasis on elemental composition of PM10 and PM2. 5. Environmental Pollution, 214, 430–439.
Saif-ul-Allah, M. W., Qyyum, M. A., Ul-Haq, N., Salman, C. A. & Ahmed, F. (2022). Gated recurrent unit coupled with projection to model plane imputation for the PM2. 5 prediction for Guangzhou City, China. Frontiers in Environmental Science, 9, 816616.
Selokar, A., Ramachandran, B., Elangovan, K. N. & Dattatreya Varma, B. (2020). PM 2.5 particulate matter and its effects in Delhi/NCR. Materials Today: Proceedings, 33, 4566–4572. https://doi.org/10.1016/j.matpr.20 20.08.187
Staudemeyer, R. C. & Morris, E. R. (2019). Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks (arXiv:1909.09586). arXiv. http://arxiv.org/abs/1909.09586
Steurer, M., Hill, R. J. & Pfeifer, N. (2021). Metrics for evaluating the performance of machine learning based automated valuation models. Journal of Property Research, 38(2), 99–129. https://doi.org/ 10.1080/095999 16.2020.1858937
Sun, W. & Li, Z. (2020). Hourly PM2.5 concentration forecasting based on mode decomposition-recombination technique and ensemble learning approach in severe haze episodes of China. Journal of Cleaner Production, 263, 121442. https://doi.org/10.1016/j.jclepro.2020.12 1442
Tran, H. D., Huang, H.-Y., Yu, J.-Y. & Wang, S.-H. (2023). Forecasting hourly PM2.5 concentration with an optimized LSTM model. Atmospheric Environment, 315, 120161. https://doi.org/10.1016/j.atmosenv.202 3.120161
Wang, H., Li, J., Peng, Y., Zhang, M., Che, H. & Zhang, X. (2019). The impacts of the meteorology features on PM2. 5 levels during a severe haze episode in central-east China. Atmospheric Environment, 197, 177–189.
Zamo, M. & Naveau, P. (2018). Estimation of the continuous ranked probability score with limited information and applications to ensemble weather forecasts. Mathematical Geosciences, 50(2), 209–234.
Bai, T., Luo, J., Zhao, J., Wen, B. & Wang, Q. (2021). Recent advances in adversarial training for adversarial robustness. arXiv Preprint arXiv:2102.01356.
Barman, N. & Gokhale, S. (2019). Urban black carbon-source apportionment, emissions and long-range transport over the Brahmaputra River Valley. Science of the Total Environment, 693, 133577.
Berrisch, J. & Ziel, F. (2023). CRPS Learning. Journal of Econometrics, 237(2), 105221. https://doi.org/10.1016/j.jeconom.2021.11.008
Bhadauria, N., Chauhan, A., Ranjan, R. & Jindal, T. (2023). An assessment of seasonal, monthly and diurnal variations of ambient air quality in the Gurugram city (Haryana). Journal of Applied and Natural Science, 15(1), Article 1. https://doi.org/10.31018/jans.v15i1.4142
Biswas, J. & Pathak, B. (2022). Effects of COVID-19 pandemic lockdown: A satellite data-based appraisal of air quality in Guwahati, Assam. Materials Today: Proceedings, 65, 2794–2800. https://doi.org/10.1016/j.matpr.2022.06.218
Chai, T. & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE). Geoscientific Model Development Discussions, 7(1), 1525–1534.
CPCB (2024). Central Pollution Control Board (CPCB). (n.d.). Retrieved January 2, 2024, from https://cpcb.nic.in/
Dutta, A., Jinsart, W., Das, U. C. & Dutta, G. (2023). An empirical analysis of Delhi’s air quality throughout different COVID-19 pandemic waves. Journal of Applied and Natural Science, 15(1), Article 1. https://doi.org/10.31018/jans.v15i1.4271
Evans, J., van Donkelaar, A., Martin, R. V., Burnett, R., Rainham, D. G., Birkett, N. J. & Krewski, D. (2013). Estimates of global mortality attributable to particulate air pollution using satellite imagery. Environmental Research, 120, 33–42.
Feng, S., Gao, D., Liao, F., Zhou, F. & Wang, X. (2016). The health effects of ambient PM2.5 and potential mechanisms. Ecotoxicology and Environmental Safety, 128, 67–74. https://doi.org/10.1016/j.ecoenv.2016.01.030
Gneiting, T. & Katzfuss, M. (2014). Probabilistic forecasting. Annual Review of Statistics and Its Application, 1, 125–151.
Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep learning. MIT press.
Hany, J. & Walters, G. (2019). Hands-On Generative Adversarial Networks with PyTorch 1. x: Implement next-generation neural networks to build powerful GAN models using Python. Packt Publishing Ltd. https://books.google.com/books?hl=en&lr=&id=URbEDwAAQBAJ&oi=fnd&pg=PP1&dq=select+optimal+discriminator+in+gan+using+pytorch&ots=WgywmebEz3&sig=Ci7g85UESAxhJ0lpwO_kRTPyUxk
Hersbach, H. (2000). Decomposition of the Continuous Ranked Probability Score for Ensemble Prediction Systems. Weather and Forecasting - WEATHER FORECAST, 15, 559–570. https://doi.org/10.1175/1520-0434(2000)015<0559:DOTCRP>2.0.CO;2
Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
Khanna, D. R., Nigam, N. S. & Bhutiani, R. (2013). Monitoring of ambient air quality in relation to traffic density in Bareilly City (U.P.), India. Journal of Applied and Natural Science, 5(2), Article 2. https://doi.org/10.31018/jans.v5i2.359
Kim, B., Kim, E., Jung, S., Kim, M., Kim, J. & Kim, S. (2023). PM2.5 Concentration Forecasting Using Weighted Bi-LSTM and Random Forest Feature Importance-Based Feature Selection. Atmosphere, 14, 968. https://doi.org/10.3390/atmos14060968
Kioumourtzoglou, M.-A., Schwartz, J. D., Weisskopf, M. G., Melly, S. J., Wang, Y., Dominici, F. & Zanobetti, A. (2016). Long-term PM2. 5 exposure and neurological hospital admissions in the northeastern United States. Environmental Health Perspectives, 124(1), 23–29.
Liu, A., Liu, X., Fan, J., Ma, Y., Zhang, A., Xie, H. & Tao, D. (2019). Perceptual-sensitive gan for generating adversarial patches. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 1028–1035. https://ojs.aaai.org/index.php/AAAI/article/view/3893
Liu, Y., Shi, G., Zhan, Y., Zhou, L. & Yang, F. (2021). Characteristics of PM2. 5 spatial distribution and influencing meteorological conditions in Sichuan Basin, southwestern China. Atmospheric Environment, 253, 118364.
Mahalakshmi, G., Sridevi, S. & Rajaram, S. (2016). A survey on forecasting of time series data. 2016 International Conference on Computing Technologies and Intelligent Data Engineering (ICCTIDE’16), 1–8.
Mangayarkarasi, R., Vanmathi, C., Khan, M. Z., Noorwali, A., Jain, R. & Agarwal, P. (2021). COVID19: Forecasting Air Quality Index and Particulate Matter (PM2. 5). Computers, Materials & Continua, 67(3). https://research.vit.ac.in/publication/covid19-forecasting-air-quality-index-and-particulate-matter-pm25/pdf/publisher-pdf-fulltext-covid19-forecasting-air-quality-index-and-particulate-matter-pm25.pdf
Medhi, S. & Gogoi, M. (2021). Visualization and Analysis of COVID-19 Impact on PM2. 5 Concentration in Guwahati city. 2021 International Conference on Computational Performance Evaluation (ComPE), 012–016.
Muruganandam, N. S. & Arumugam, U. (2023). Dynamic Ensemble Multivariate Time Series Forecasting Model for PM2. 5. Computer Systems Science & Engineering, 44(2). https://cdn.techscience.cn/ueditor/files/csse/TSP_ CSSE-44-2/TSP_CSSE_24943/TSP_CS SE_24943.pdf
O’Donnell, M. J., Fang, J., Mittleman, M. A., Kapral, M. K. & Wellenius, G. A. (2011). Fine Particulate Air Pollution (PM2.5) and the Risk of Acute Ischemic Stroke. Epidemiology (Cambridge, Mass.), 22(3), 422–431. https://doi.org/10.1097/EDE.0b013e3182126580
Oliveira, M., Slezakova, K., Delerue-Matos, C., Pereira, M. C. & Morais, S. (2016). Assessment of air quality in preschool environments (3–5 years old children) with emphasis on elemental composition of PM10 and PM2. 5. Environmental Pollution, 214, 430–439.
Saif-ul-Allah, M. W., Qyyum, M. A., Ul-Haq, N., Salman, C. A. & Ahmed, F. (2022). Gated recurrent unit coupled with projection to model plane imputation for the PM2. 5 prediction for Guangzhou City, China. Frontiers in Environmental Science, 9, 816616.
Selokar, A., Ramachandran, B., Elangovan, K. N. & Dattatreya Varma, B. (2020). PM 2.5 particulate matter and its effects in Delhi/NCR. Materials Today: Proceedings, 33, 4566–4572. https://doi.org/10.1016/j.matpr.20 20.08.187
Staudemeyer, R. C. & Morris, E. R. (2019). Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks (arXiv:1909.09586). arXiv. http://arxiv.org/abs/1909.09586
Steurer, M., Hill, R. J. & Pfeifer, N. (2021). Metrics for evaluating the performance of machine learning based automated valuation models. Journal of Property Research, 38(2), 99–129. https://doi.org/ 10.1080/095999 16.2020.1858937
Sun, W. & Li, Z. (2020). Hourly PM2.5 concentration forecasting based on mode decomposition-recombination technique and ensemble learning approach in severe haze episodes of China. Journal of Cleaner Production, 263, 121442. https://doi.org/10.1016/j.jclepro.2020.12 1442
Tran, H. D., Huang, H.-Y., Yu, J.-Y. & Wang, S.-H. (2023). Forecasting hourly PM2.5 concentration with an optimized LSTM model. Atmospheric Environment, 315, 120161. https://doi.org/10.1016/j.atmosenv.202 3.120161
Wang, H., Li, J., Peng, Y., Zhang, M., Che, H. & Zhang, X. (2019). The impacts of the meteorology features on PM2. 5 levels during a severe haze episode in central-east China. Atmospheric Environment, 197, 177–189.
Zamo, M. & Naveau, P. (2018). Estimation of the continuous ranked probability score with limited information and applications to ensemble weather forecasts. Mathematical Geosciences, 50(2), 209–234.
Issue
Section
Research Articles
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
This work is licensed under Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) © Author (s)
How to Cite
PM2.5 concentration prediction using Generative adversarial network: A novel approach. (2024). Journal of Applied and Natural Science, 16(2), 704-712. https://doi.org/10.31018/jans.v16i2.5510
