Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2024, Vol. 21, No. 2, pp. 336-349

Development of a new automatic method for reconstructing the intensity of tropical cyclones from multispectral satellite Earth observations using artificial neural networks

A.N. Yakusheva 1 , D.M. Ermakov 1, 2 
1 Space Research Institute RAS, Moscow, Russia
2 Kotelnikov Institute of Radioengineering and Electronics RAS, Fryazino Branch, Fryazino, Moscow Region, Russia
Accepted: 29.03.2024
DOI: 10.21046/2070-7401-2024-21-2-336-349
The paper presents an automatic method for reconstructing the intensity of tropical cyclones (TCs) from their satellite images, based on a convolutional neural network. To form a sample of initial data, 43688 records of TCs from the databases of the main regional national tropical cyclone monitoring centers (for brevity, “national hurricane centers”, NHC DB) and corresponding satellite images in several spectral ranges (visible, IR, microwave) were used. The collected data covers observations from 1981 to 2022 in all areas of the World Ocean, except the Indian Ocean, involved in the genesis of tropical cyclones. A study was carried out on the implementation of a neural network with the best performance, restoring the intensity of TCs using the collected volume of data. Based on the results of the study, a neural network was designed, implemented and trained, which provided (when comparing the reconstructed TC intensity value with those indicated in the NHC DB) a root mean square error of about 11.3 (11.4) nodes; the coefficient of determination is about 0.80 (0.82) depending on the combination of types of input information. It is noted that the achieved quality indicators exceed those known from the literature or are comparable to them. At the same time, an analysis of works on the development of approaches to automated assessment of TC intensity showed that all of them were carried out using significantly (orders of magnitude) smaller volumes of input information (individual water areas, single years, certain phases of TC development, etc.). Estimates of the root-mean-square error stated in the literature range from 8 to 14 knots, but the minimum level of error is achieved through special selection of “suitable” data.
Keywords: tropical cyclones, intensity retrievals, artificial neural networks, multispectral satellite observations
Full text

References:

  1. Arohan A., Koustav A., Abhishek S., A Review of Convolutional Neural Networks, 2020 Intern. Conf. Emerging Trends in Information Technology and Engineering, 2020, pp. 1–5, DOI: 10.1109/ic-ETITE47903.2020.049.
  2. Bai L., Tang J., Guo R., Zhang S., Quantifying interagency differences in intensity estimations of Super Typhoon Lekima (2019), Frontiers of Earth Science, 2022, Vol. 16, pp. 5–16, DOI: 10.1007/s11707-020-0866-5.
  3. Chen B.-F., Chen B., Lin H.-T., Elsberry R. L., Estimating tropical cyclone intensity by satellite imagery utilizing convolutional neural networks, Weather and Forecasting, 2019, Vol. 34, No. 2, pp. 447–465, https://doi.org/10.1175/WAF-D-18-0136.1.
  4. Combinido J. S., Mendoza J. R., Aborot J., A convolutional neural network approach for estimating tropical cyclone intensity using satellite-based infrared images, Proc. 24 th Intern. Conf. Pattern Recognition (ICPR-2018), 2018, pp. 1474–1480, DOI: 10.1109/ICPR.2018.8545593.
  5. Dvorak V. F., A Technique for the Analysis and Forecasting of Tropical Cyclone Intensities from Satellite Pictures, Washington, D. C.: National Oceanic and Atmospheric Administration, 1973, 25 p., https://repository.library.noaa.gov/view/noaa/18546.
  6. Kingma D. P., Ba J. L., Adam: A method for stochastic optimization, Proc. 3rd Intern. Conf. Learning Representations (ICLR, 2015), 2015, 15 p., http://arxiv.org/abs/1412.6980.
  7. Lee J., Im J., Cha D.-H. et al., Tropical cyclone intensity estimation using multi-dimensional convolutional neural networks from geostationary satellite data, Remote Sensing, 2020, Vol. 12, Issue 1, Article 108, https://doi.org/10.3390/rs12010108.
  8. Sharkov E. A., Global Tropical Cyclogenesis, Berlin; Heidelberg; London; New York etc.: Springer/PRAXIS, 2000, 361 p.
  9. Sharkov E. A., Global tropical cyclogenesis. 2 nd ed., Berlin, Heidelberg: Springer-Verlag, 2012, 604 p.
  10. Sun H., Lei X., Tang J., Yao L., Comparisons of the characteristics of tropical cyclones experiencing extratropical transition in the western north pacific based on different dataset, J. Tropical Meteorology, 2017, Vol. 23, No. 3, DOI: 10.16555/j.1006-8775.2017.03.005.
  11. Velden C. S., Herndon D., An update on the SATellite CONsensus (SATCON) algorithm for estimating tropical cyclone intensity, Proc. 31st Conf. Hurricanes and Tropical Meteorology, 2014, https://tropic.ssec.wisc.edu/misc/satcon/hurrconf_2014_satcon_poster.pdf.
  12. Wimmers A., Velden C., Joshua C., Using deep learning to estimate tropical cyclone intensity from satellite passive microwave imagery, Monthly Weather Review, 2019, Vol. 147, No. 6, pp. 2261–2282, https://doi.org/10.1175/MWR-D-18-0391.1.
  13. Xiang K., Yang X., Zhang M. et al., Objective Estimation of Tropical Cyclone Intensity from Active and Passive Microwave Remote Sensing Observations in the Northwestern Pacific Ocean, Remote Sensing, 2019, Vol. 11, No. 6, Article 627, DOI: 10.3390/rs11060627.
  14. Yang S., Gossuth J., Satellite remote sensing of tropical cyclones, In: Recent Developments in Tropical Cyclone Dynamics, Prediction, and Detection, Lupo A. R. (ed.), 2016, DOI: 10.5772/64114.
  15. Yu H., Hu C., Jiang L., Comparison of three tropical cyclone strength datasets, J. Meteorological Research, 2007, Vol. 21, No. 1, pp. 121–128.
  16. Zhao Y., Zhao C., Sun R., Wang Z., A multiple linear regression model for tropical cyclone intensity estimation from satellite infrared images, Atmosphere, 2016. Vol. 7, No. 40, https://doi.org/10.3390/atmos7030040.