Visually Estimating and Forecasting PM2.5 Levels Using Hybrid Architecture Deep Neural Network
Article Sidebar
Main Article Content
Abstract
Air pollutants, particularly particulate matter with a diameter of less than 2.5 microns (PM2.5), have been linked to a number of negative climatic and health effects, including irritation and damage to internal organs in the short and long term. Knowing current and future levels of PM2.5 is therefore crucial for both public health and environmental management. Photos of the sky and buildings can aid in assessing visibility and air quality because PM2.5 alters the appearance of the sky and its surroundings. This research proposes a method that employs digital images to not only estimate but also forecast PM2.5 concentration levels using deep learning technologies. A convolutional neural network (CNN) was used as the base layer to automatically extract image features, while a long short-term memory (LSTM) network was used as the output layer to analyze the sequence of features. The sky and its surroundings were captured hourly from a high-rise building in Bangkok, Thailand, and the ground-truth PM2.5 data were obtained from the nearest monitoring station facing the same direction. The experimental results show that the hybrid CNN and LSTM model outperformed conventional CNN models in estimating and forecasting PM2.5 levels by 5% and 30%, respectively.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright Transfer Statement
The copyright of this article is transferred to Current Applied Science and Technology journal with effect if and when the article is accepted for publication. The copyright transfer covers the exclusive right to reproduce and distribute the article, including reprints, translations, photographic reproductions, electronic form (offline, online) or any other reproductions of similar nature.
The author warrants that this contribution is original and that he/she has full power to make this grant. The author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors.
Here is the link for download: Copyright transfer form.pdf
References
Bazyar, J., Pourvakhshoori, N., Khankeh, H., Farrokhi, M., Delshad, V. and Rajabi, E., 2019. A comprehensive evaluation of the association between ambient air pollution and adverse health outcomes of major organ systems: a systematic review with a worldwide approach. Environmental Science and Pollution Research, 26(13), 12648-12661, https://doi.org/10.1007/s11356-019-04874-z.
Kuylenstierna, J., Malley, C., Büker, P., and Marmon, T., 2020. Air Pollution and Its Impact on Human Health: An Important Driver for Achieving the 1.5°C Goal of the Intergovernmental Panel on Climate Change. [online] Available at : https://www.sei.org/publications/air-pollution-and-human-health-impacts/.
Shi, L., Wu, X., Yazdi, M.D., Braun, D., Awad, Y.A., Wei, Y., Liu, P., Di, Q., Wang, Y., Schwartz, J., Dominici, F., Kioumourtzoglou, M.-A. and Zanobetti, A., 2020. Long-term effects of PM2.5 on neurological disorders in the American Medicare population: a longitudinal cohort study. The Lancet Planetary Health, 4(12), e557-e565, https://doi.org/10.1016/s2542-5196(20)30227-8.
Tai, A.P.K., Mickley, L.J. and Jacob, D.J., 2010. Correlations between fine particulate matter (PM2.5) and meteorological variables in the United States: Implications for the sensitivity of PM2.5 to climate change. Atmospheric Environment, 44(32), 3976-3984, https://doi.org/10.1016/j.atmosenv.2010.06.060.
Ren-Jian, Z., Ho, K.F. and Zhen-Xing, S., 2012. The role of aerosol in climate change, the environment, and human health. Atmospheric and Oceanic Science Letters, 5(2), 156-161, https://doi.org/10.1080/16742834.2012.11446983.
Pollution Control Department, 2019. Air4Thai. [online] Available at : http://air4thai.pcd.go.th/.
Chen, T.-F., Tsai, C.-Y. and Chang, K.-H., 2013. Performance evaluation of atmospheric particulate matter modeling for East Asia. Atmospheric Environment, 77, 365-375, https://doi.org/10.1016/j.atmosenv.2013.05.025.
Mehmood, K., Bao, Y., Saifullah, Cheng, W., Khan, M.A., Siddique, N., Abrar, M.M., Soban, A., Fahad, S. and Naidu, R., 2022. Predicting the quality of air with machine learning approaches: Current research priorities and future perspectives. Journal of Cleaner Production, 379 Part 2, https://doi.org/10.1016/j.jclepro.2022.134656.
Zhang, B., Rong, Y., Yong, R., Qin, D., Li, M., Zou, G. and Pan, J., 2022. Deep learning for air pollutant concentration prediction: A review. Atmospheric Environment, 290, https://doi.org/10.1016/j.atmosenv.2022.119347.
US EPA, 2022. Health and environmental effects of particulate matter (PM). [online] Available at : https://www.epa.gov/pm-pollution/health-and-environmental-effects-particulate-matter-pm.
Yao, L., Kong, S., Zheng, H., Chen, N., Zhu, B., Xu, K., Cao, W., Zhang, Y. Zheng, M., Cheng, Y., Hu, Y., Zhang, Z., Yan,Y. Liu, D., Zhao, T., Bai, Y. and Qi, S., 2021. Co-benefits of reducing PM2.5 and improving visibility by covid-19 lockdown in Wuhan. npj Climate and Atmospheric Science, 4(1), https://doi.org/10.1038/s41612-021-00195-6.
Liu, C., Tsow, F., Zou, Y. and Tao, N., 2016. Particle pollution estimation based on image analysis. PLoS ONE, 11(2), 1-14, https://doi.org/10.1371/journal.pone.0145955.
He, Z., Ye, X., Gu, K. and Qiao, J., 2018. Learn to predict pm2.5 concentration with image contrast-sensitive features. Proceedings of the 2018 37th Chinese Control Conference (CCC), Wuhan, China, July 25-27, 2018, pp. 4102-4106.
Chen, Q., Chen, W. and Pan, G., 2021. An improved picture-based prediction method of PM2.5 concentration. IET Image Processing, 16(11), 2827-2833, https://doi.org/10.1049/ipr2.12204.
Wang, G., Shi, Q. and Jiang, K., 2022. PM2.5 concentration measurement based on image perception. Electronics, 11(9), https://doi.org/10.3390/electronics11091298.
Yao, S., Wang, F. and Huang, B., 2022. Measuring PM2.5 concentrations from a single smartphone photograph. Remote Sensing, 14(11), https://doi.org/10.3390/rs14112572.
Al-Saffar, A.A.M., Tao, H., and Talab, M.A., 2017. Review of deep convolution neural network in image classification. Proceedings of the 2017 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET), Jakarta, Indonesia, October 23-24, 2017, pp. 26-31.
Schultz, M.G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen, L.H., Mozaffari, A. and Stadtler, S., 2021. Can deep learning beat numerical weather prediction? Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 379(2194), https://doi.org/10.1098/rsta.2020.0097.
Zhang, C., Yan, J., Li, C., Rui, X., Liu, L. and Bie, R., 2016. On estimating air pollution from photos using convolutional neural network. Proceedings of the 24th ACM International Conference on Multimedia (MM), Amsterdam, The Netherlands, October 15-19, 2016, pp. 297-301.
Zhang, C., Yan, J., Li, C., Wu, H. and Bie, R., 2018. End-to-end learning for image-based air quality level estimation. Machine Vision and Applications, 29(4), 601-615, https://doi.org/10.1007/s00138-018-0919-x.
Jiang, Z., Zheng, T., Bergin, M. and Carlson, D., 2022. Improving spatial variation of ground-level PM2.5 prediction with contrastive learning from satellite imagery. Science of Remote Sensing, 5, https://doi.org/10.1016/j.srs.2022.100052.
Zaini, N., Ean, L.W., Ahmed, A.N. and Malek, M.A., 2022. A systematic literature review of deep learning neural network for time series air quality forecasting. Environmental Science and Pollution Research, 29(13), 4958-4990, https://doi.org/10.1007/s11356-021-17442-1.
Chen, H.-C., Putra, K.T., Weng, C.-E. and Lin, J.C.-W., 2022. A novel predictor for exploring PM2.5 spatiotemporal propagation by using convolutional recursive neural networks. Journal of Internet Technology, 23(1), 165-176.
Jiang, X., Luo, Y. and Zhang, B., 2021. Prediction of PM2.5 concentration based on the LSTM-TSLightGBM variable weight combination model. Atmosphere, 12(9), https://doi.org/10.3390/atmos12091211.
Shi, L., Zhang, H., Xu, X., Han, M. and Zuo, P., 2022. A balanced social LSTM for PM2.5 concentration prediction based on local spatiotemporal correlation. Chemosphere, 291(Part 3), https://doi.org/10.1016/j.chemosphere.2021.133124.
Song, S., Lam, J.C.K., Han, Y. and Li, V.O.K., 2020. ResNet-LSTM for real-time PM2.5 and PM10 estimation using sequential smartphone images. IEEE Access, 8(99), 220069-220082, https://doi.org/10.1109/ACCESS.2020.3042278.
Won, T., Eo, Y.D., Sung, H., Chong, K.S., Youn, J. and Lee, G.W., 2022. Particulate matter estimation from public weather data and closed-circuit television images. KSCE Journal of Civil Engineering, 26, 865-873, https://doi.org/10.1007/s12205-021-0865-4.
Yu, Y., Si, X., Hu, C. and Zhang, J., 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 31(7), 1235-1270, https://doi.org/10.1162/neco_a_01199.
Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory. Neural Computation, 9(8), 1735-1780, https://doi.org/10.1162/neco.1997.9.8.1735.
Zhao, F., Feng, J., Zhao, J., Yang, W. and Yan, S., 2018. Robust LSTM-autoencoders for face de-occlusion in the wild. IEEE Transactions on Image Processing, 27(2), 778-790, https://doi.org/10.1109/TIP.2017.2771408.
Peng-in, B., Sanitluea, P., Monjatturat, P., Boonkerd, P. and Phosri, A., 2022. Estimating ground-level PM2.5 over Bangkok metropolitan region in Thailand using aerosol optical depth retrieved by MODIS. Air Quality, Atmosphere and Health, 15(11), 2091-2102, https://doi.org/10.1007/s11869-022-01238-4.
Zeng, A., Chen, M., Zhang, L. and Xu, Q., 2023. Are transformers effective for time series forecasting? Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-23), Washington DC, USA, February 7-14, 2023, pp. 11121-11128.