On monitoring and forecasting the dynamics of the development of the structure of tropical cyclones based on almost periodic analysis of satellite images

Objectives. The article sets out to identify the characteristics of tropical cyclones using almost periodic analysis of images of cloud dynamics of hurricanes in order to forecast the cyclone structure. Almost periodic analysis is applied in the processing and analysis of tropical cyclone structure images based on the obtained almost period values using a modified mathematical computational apparatus.

Methods. The main tool for processing and analyzing images of the tropical cyclone structure is almost periodic analysis, i.e., analysis of data with an ordered argument to identify dependencies that are close to periodic. By this means critical boundaries of changes in the trends of the studied data can be identified regardless of a priori assumptions. In the course of analysis the almost period information parameter, corresponding to the values closest to the periods, is determined. A modification of the known mathematical apparatus of almost periodic analysis is proposed for processing large and multidimensional datasets.

Results. In the course of the study, the characteristic almost periodic values of the structural zones at the moment of the beginning of the formation of the dynamics of the cyclone development were revealed on the example of the analysis of the frames of the dynamics of tropical cyclone Milton, operating from October 5, 2024 to October 10, 2024. Based on the identified values, forecast estimates of the tropical cyclone structure development were made to an accuracy of 95%.

Conclusions. Together with the results of studies published earlier, the results of this study support the conclusion that it is possible to apply almost periodic analysis to the identification of characteristic patterns of tropical cyclone structures and carry out qualitative forecast estimates of the dynamics of emergency situations caused by tropical cyclones. 

1. Donatelli R.E., Park J.A., Matthews S.M., Lee S.D. Time series analysis. Am. J. Orthod. Dentofacial Orthop. 2022;161(4): 605–608. https://doi.org/10.1016/j.ajodo.2021.07.013

2. Seibert J., Gross Y., Schrott C. A systematic review of packages for time series analysis. Eng. Proc. 2021;5(1):22. https://doi.org/10.3390/engproc2021005022

3. Choi K., Yi J., Park K., Yoon S. Deep learning for anomaly detection in time series data: A review, analysis, and guidelines. IEEE Access. 2021;9:120043–120065. https://doi.org/10.1109/ACCESS.2021.3107975

4. Kumar R., Kumar P., Kumar Y. Multi-step time series analysis and forecasting strategy using ARIMA and evolutionary algorithms. Int. J. Inf. Technol. 2022;14(1):359–373. https://doi.org/10.1007/s41870-021-00741-8

5. Dubey A.K., Kumar A., Garcia-Diaz V., Sharma A.K., Kanhaiya K. Study and analysis SARIMA and LSTM in forecasting time series data. Sustainable Energy Technologies and Assessments. 2021;47:101474. https://doi.org/10.1016/j.seta.2021.101474

6. Pashshoev B., Petrusevich D.A. Neural network analysis in time series forecasting. Russ. Technol. J. 2024;12(4):106–116. https://doi.org/10.32362/2500-316X-2024-12-4-106-116

7. Mokhnatkina U.S., Parfenov D.V., Petrusevich D.A. Analysis of approaches to identification of trend in the structure of the time series. Russ. Technol. J. 2024;12(3):93–103. https://doi.org/10.32362/2500-316X-2024-12-3-93-103

8. Perova J.P., Lesko S.A., Ivanov A.A. Analyzing and forecasting the dynamics of Internet resource user sentiments based on the Fokker–Planck equation. Russ. Technol. J. 2024;12(3):78–92. https://doi.org/10.32362/2500-316X-2024-12-3-78-92

9. Gramovich I.V., Musatov D.Yu., Petrusevich D.A. Implementation of bagging in time series forecasting. Russ. Technol. J. 2024;12(1):101–110. https://doi.org/10.32362/2500-316X-2024-12-1-101-110

10. Kracalik I., Mowla S., Katz L., Cumming M., Sapiano M.R., Basavaraju S.V. Impact of the early coronavirus disease 2019 pandemic on blood utilization in the United States: A time series analysis of data submitted to the National Healthcare Safety Network Hemovigilance Module. Transfusion. 2021;61(Suppl. 2):S36–S43. https://doi.org/10.1111/trf.16451

11. Kumar R., Jain A., Tripathi A.K., Tyagi S. COVID-19 outbreak: An epidemic analysis using time series prediction model. In: 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence). 2021. IEEE. P. 1090–1094. https://doi.org/10.1109/Confluence51648.2021.9377075

12. Balli S. Data analysis of COVID-19 pandemic and short-term cumulative case forecasting using machine learning time series methods. Chaos Solitons Fractals. 2021;142:110512. https://doi.org/10.1016/j.chaos.2020.110512

13. Chen X., Wang X., Zhang K., Fung K.M., Thai T.C., Moore K., Mannel R.S., Liu H., Zheng B., Qiu Y. Recent advances and clinical applications of deep learning in medical image analysis. Med. Image Anal. 2022;79:102444. https://doi.org/10.1016/j.media.2022.102444

14. Suganyadevi S., Sithalakshmi V., Balasami K. A review on deep learning in medical image analysis. Int. J. Multimed. Info. Retr. 2022;11(1):19–38. https://doi.org/10.1007/s13735-021-00218-1

15. Van der Velden B.H., Kuijf H.J., Gilhuis K.G., Virgeever M.A. Explainable artificial intelligence (XAI) in deep learningbased medical image analysis. Med. Image Anal. 2022;79:102470. https://doi.org/10.1016/j.media.2022.102470

16. Meyer-Hein L., Reinke A., Godau P., et al. Metrics reloaded: Pitfalls and recommendations for image analysis validation. arXiv. 2022 Jul 7; arXiv:2206.01653. https://doi.org/10.48550/arXiv.2206.01653

17. Fu Y., Zhu Z., Liu L., Zhan W., He T., Shen H., Zhao J., Liu Y., Zhang H., Liu Z., Xue Y. Remote sensing time series analysis: A review of data and applications. J. Remote Sens. 2024;4:0285. https://doi.org/10.34133/remotesensing.0285

18. Richards J.A. Remote Sensing Digital Image Analysis. Berlin/Heidelberg, Germany: Springer; 2022. 567 p. https://doi.org/10.1007/978-3-030-82327-6

19. Krynetskiy B.A. Analysis of models of periodic structures of spatiotemporal processes. In: Actual Problems of Applied Mathematics, Informatics, and Mechanics: Proceedings of the International Scientific Conference. Voronezh; 2024. P. 497–501 (in Russ.). https://elibrary.ru/vbsjnl

20. Kuzmin V.I., Gadzaov A.F. Mathematical methods of analysis of periodic components of nonlinear processes and predict the dynamics of the limited growth based on them. Vestnik MGTU MIREA = Herald of MSTU MIREA (Russ. Technol. J.). 2015;4-2(9):94–104 (in Russ.). https://elibrary.ru/vhiyoz

21. Kuzmin V.I., Samokhin A.B. Almost periodic functions with trend. Vestnik MGTU MIREA = Herald of MSTU MIREA (Russ. Technol. J.). 2015;4-2(9):105–110 (in Russ.). https://elibrary.ru/vhiypj

22. Paramonov A.A., Krynetskiy B.A. Asymptotic analysis of an algorithm for searching for almost-periods in data with an ordered argument. Zashchita informatsii. Insait. 2023;4(112):53–57 (in Russ.).

23. Kalach A.V., Paramonov A.A., Tolstova I.S., Danilova V.A. Program for Almost-Periodic Data Processing with Parallel Computing Option: Computer Program RU2024688438 RF. Publ. 13.02.2025 (in Russ.).

24. Paramonov A.A. Identification of almost-periodic characteristics of satellite images of typhoons in the aspect of solving problems of technosphere safety. Tekhnosfernaya bezopasnost’ = Technosphere Safety. 2024;44(3):71–76 (in Russ.).

25. Paramonov A.A., Kalach A.V. Simulation of emergencies using almost periodic analysis of images of typhoon structure. Vestnik Yuzhno-Ural’skogo gosudarstvennogo universiteta. Seriya: Matematika. Mekhanika. Fizika = Bulletin of the South Ural State University. Series: Mathematics. Mechanics. Physics. 2024;16(4):67–74 (in Russ.). http://doi.org/10.14529/10.14529/mmph240408

26. Kalach A.V., Paramonov A.A. On the possibilities of using the method of near-periodic analysis method for image processing. Modelirovanie sistem i protsessov = Modeling of Systems and Processes. 2024;17(3):44–52 (in Russ.). http://doi.org/10.12737/2219-0767-2024-42-50

27. Fridzon M.B., Evtushenko O.A. About requirements for exactness of meteo information. Nauchnyi vestnik Moskovskogo gosudarstvennogo tekhnicheskogo universiteta grazhdanskoi aviatsii (Nauchnyi Vestnik MGTU GA) = Civil Aviation High Technologies. 2014;210:142–144 (in Russ.). https://elibrary.ru/tbubqh

28. Wang X., Chen K., Liu L., Han T., Li B., Bai L. Global tropical cyclone intensity forecasting with multi-modal multiscale causal autoregressive model. In: ICASSP 2025–2025 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE; 2025. P. 1–5. https://doi.org/10.1109/ICASSP49660.2025.10888556