Satellite remote sensing and deep learning for aerosols prediction

  • Nikola S. Mirkov University of Belgrade, ”Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of Serbia https://orcid.org/0000-0002-3057-9784
  • Dušan S. Radivojević University of Belgrade, ”Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of Serbia https://orcid.org/0000-0003-1959-3152
  • Ivan M. Lazović University of Belgrade, ”Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of Serbia https://orcid.org/0000-0002-3877-5157
  • Uzahir R. Ramadani University of Belgrade, ”Vinča” Institute of Nuclear Sciences - National Institute of the Republic of Serbia, Belgrade, Republic of Serbia https://orcid.org/0000-0002-3702-0094
  • Dušan P. Nikezić University of Belgrade, VINČA Institute of Nuclear Sciences ­ - National Institute of the Republic of Serbia, Belgrade, Republic of Serbia https://orcid.org/0000-0002-8885-2683
Keywords: aerosol optical thickness, NASA Earth observations, ConvL-STM2D, COVID-19, particulate matter dispersion

Abstract


Introduction/purpose: The paper presents a new state-of-the-art method that involves NASA satellite imagery with the latest deep learning model for a spatiotemporal sequence forecasting problem. Satellite-retrieved aerosol information is very useful in many fields such as PM prediction or COVID-19 transmission. The input data set was MODAL2_E_AER_OD which presents global AOT for every 8 days from Terra/MODIS. The im plemented machine learning algorithm was built with ConvLSTM2D lay ers in Keras. The obtained results were compared with the new CNN LSTM model.

Methods: Computational methods of Machine Learning, Artificial Neural Networks, Deep Learning.

Results: The results show global AOT prediction obtained using satellite digital imagery as an input.

Conclusion: The results show that the ConvLSTM developed model could be used for global AOT prediction, as well as for PM and COVID-19 transmission.

References

Beer, C.G., Hendricks, J., Righi, M., Heinold, B., Tegen, I., Groß, S., Sauer, D., Walser, A. & Weinzierl, B. 2020. Modelling mineral dust emissions and atmo- spheric dispersion with MADE3 in EMAC v2. 54. Geoscientific Model Develop- ment, 13(9), pp. 4287–4303. Available at: https://doi.org/10.5194/gmd-13-4287-2020,2020

Colbeck, I. & Lazaridis, M. 2013. Introduction. In: Colbeck, I. and Lazaridis, M. (Eds.) Aerosol Science. Wiley Online Library. Available at: https://doi.org/10.1002/9781118682555.ch1.

Dey, P., Chaulya, S. & Kumar, S. 2021. Hybrid CNN-LSTM and IoT-based coal mine hazards monitoring and prediction system. Process Safety and Environmen- tal Protection, 152, pp. 249–263. Available at: https://doi.org/10.1016/j.psep.2021.06.005

Ding, X., Feng, L., Zou, Y. & Zhang, G. 2020. Deep learning aided spectrum prediction for satellite communication systems. IEEE Transactions on Vehicular Technology, 69(12), pp. 16314–16319. Available at: https://doi.org/10.1109/TVT.2020.3043837

Donahue, J., Hendricks, A.L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T. & Saenko, K. 2015. Long-term recurrent convolutional networks for visual recognition and description. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). p. . Boston, MA, USA, pp.2625-2634, June 07-12. Available at: https://doi.org/10.1109/CVPR.2015.7298878

Eleftheriadis, K., Gini, M.I., Diapouli, E., Vratolis, S., Vasilatou, V., Fetfatzis, P. & Manousakas, M.I. 2021. Aerosol microphysics and chemistry reveal the COVID19 lockdown impact on urban air quality. Scientific Reports, 11, art.number:14477. Available at: https://doi.org/10.1038/s41598-021-93650-6

Elperin, T., Fominykh, A., Katra, I. & Krasovitov, B. 2017. Modeling of gas adsorption by aerosol plumes emitted from industrial sources. Process Safety and Environmental Protection, 111, pp. 375–387. Available at: https://doi.org/10.1016/j.psep.2017.06.022

Filonchyk, M., Yan, H., Zhang, Z., Yang, S., Li, W. & Li, Y. 2019. Combined use of satellite and surface observations to study aerosol optical depth in different regions of China. Scientific reports, 9(art.number:6174), pp. 1–15. Available at: https://doi.org/10.1038/s41598-019-42466-6

Hochreiter, S. & Schmidhuber, J. 1997. Long short-term memory. Neural com- putation, 9(8), pp. 1735–1780. Available at: https://doi.org/10.1162/neco.1997.9.8.1735

Hu, W.S., Li, H.C., Pan, L., Li, W., Tao, R. & Du, Q. 2020. Spatial–spectral feature extraction via deep ConvLSTM neural networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 58(6), pp. 4237–4250. Available at: https://doi.org/10.1109/TGRS.2019.2961947

Kumar, N., Chu, A. & Foster, A. 2007. An empirical relationship between PM2. 5 and aerosol optical depth in Delhi Metropolitan. Atmospheric Environment, 41(21), pp. 4492–4503. Available at: https://doi.org/10.1016/j.atmosenv.2007.01.046

Lin, C., Liu, G., Lau, A.K.H., Li, Y., Li, C., Fung, J.C.H. & Lao, X.Q. 2018. High-resolution satellite remote sensing of provincial PM2. 5 trends in China from 2001 to 2015. Atmospheric environment, 180, pp. 110–116. Available at: https://doi.org/10.1016/j.atmosenv.2018.02.045

NASA Goddard Space Flight Center, 2022. AERONET Aerosol Robotic Net- work, [online]. Available at: https://aeronet.gsfc.nasa.gov/ [Accessed: 1 Septem- ber 2022].

NASA NEO Nasa Earth Observations, 2022a. Index of /archive/rgb, [online]. Available at: https://neo.gsfc.nasa.gov/archive/rgb/ [Accessed: 1 September 2022].

NASA    NEO    Nasa    Earth    Observations,     2022b.              Index    of /archive/rgb/MODAL2_E_AER_OD, [online].    Available at: https://neo.gsfc.nasa.gov/archive/rgb/MODAL2_E_AER_OD/ [Accessed: 1 September 2022].

Nikezić, D.P., Gršić, Z.J., Dramlić, D.M., Dramlić, S.D., Lončar, B.B. & Dimović, S.D. 2017. Modeling air concentration of fly ash in Belgrade, emitted from thermal power plants TNTA and TNTB. Process Safety and Environmental Protection, 106, pp. 274–283. Available at: https://doi.org/10.1016/j.psep.2016.06.009

Nikezić, D.P., Ramadani, U.R., Radivojević, D.S., Lazović, I.M. & Mirkov, N.S. 2022. Deep Learning Model for Global Spatio-Temporal Image Prediction. Math- ematics, 10(18,art.ID:3392), pp. 1–5. Available at: https://doi.org/10.3390/math10183392

Radivojević, D.S., Mirkov, N.S. & Maletić, S. 2021. Human activity recognition based on machine learning classification of smartwatch accelerometer dataset. FME Transactions, 49(1), pp. 225–232. Available at: https://doi.org/10.5937/fme2101225R

Shi, S., Cheng, T., Gu, X., Guo, H., Wu, Y., Wang, Y., Bao, F. & Zuo, X. 2020. Probing the dynamic characteristics of aerosol originated from South Asia biomass burning using POLDER/GRASP satellite data with relevant accessory technique design. Environment International, 145, art.number:106097. Available at: https://doi.org/10.1016/j.envint.2020.106097

Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K. & Woo, W.c. 2015. Con- volutional LSTM Network: A Machine Learning Approach for Precipitation Now- casting. arXiv:1506.04214. Available at: https://doi.org/10.48550/arXiv.1506.04214

Tang, S., Mao, Y., Jones, R.M., Tan, Q., Ji, J.S., Li, N., Shen, J., Lv, Y., Pan, L., Ding, P. et al. 2020. Aerosol transmission of SARS-CoV-2? Evidence, preven- tion and control. Environment international, 144, art.number:106039, pp. 1–10. Available at: https://doi.org/10.1016/j.envint.2020.106039

Vaddi, R. & Manoharan, P. 2020. Hyperspectral image classification using CNN with spectral and spatial features integration. Infrared Physics & Technology, 107, art.number:103296. Available at: https://doi.org/10.1016/j.infrared.2020.103296

Valueva, M.V., Nagornov, N., Lyakhov, P.A., Valuev, G.V. & Chervyakov, N.I. 2020. Application of the residue number system to reduce hardware costs of the convolutional neural network implementation. Mathematics and computers in sim- ulation, 177, pp. 232–243. Available at: https://doi.org/10.1016/j.matcom.2020.04.031

Wang, Z., Liu, Y., Hu, M., Pan, X., Shi, J., Chen, F., He, K., Koutrakis, P. & Christiani, D.C. 2013. Acute health impacts of airborne particles estimated from satellite remote sensing. Environment international, 51, pp. 150–159. Available at: https://doi.org/10.1016/j.envint.2012.10.011

Wei, X., Chang, N.B., Bai, K. & Gao, W. 2020. Satellite remote sensing of aerosol optical depth: Advances, challenges, and perspectives. Critical Reviews in Environmental Science and Technology, 50(16), pp. 1640–1725. Available at: https://doi.org/10.1080/10643389.2019.1665944

Xavier, A. 2019. An introduction to ConvLSTM. Medium. [online]. Available at: https://medium.com/neuronio/an-introduction-to-convlstm-55c9025563a7 [Accessed: 1 September 2022].

You, W., Zang, Z., Zhang, L., Li, Y., Pan, X. & Wang, W. 2016. National- scale estimates of ground-level PM2. 5 concentration in China using geographi- cally weighted regression based on 3 km resolution MODIS AOD. Remote Sens- ing, 8(3, art.ID:184), pp. 1–13. Available at: https://doi.org/10.3390/rs8030184

Zoran, M.A., Savastru, R.S., Savastru, D.M., Tautan, M.N., Baschir, L.A. & Tenciu, D.V. 2021. Exploring the linkage between seasonality of environmental factors and COVID-19 waves in Madrid, Spain. Process Safety and Environmental Protection, 152, pp. 583–600. Available at: https://doi.org/10.1016/j.psep.2021.06.043

 

Published
2023/01/30
Section
Original Scientific Papers