Russian Federation
Russian Federation
The article addresses the issue of improving the accuracy of damage forecasting from natural emergencies while taking anthropogenic factors into account. It is demonstrated that ignoring these factors leads to unreliable damage assessments and inefficient planning of protective measures. An approach is proposed that integrates meteorological and anthropogenic indicators into a unified model using a neural network. The model enables simultaneous damage forecasting and justification of the volumes of engineering and technical measures, contributing to a more rational allocation of resources and a reduction in overall losses from emergencies.
damage forecasting, emergencies, anthropogenic factors, engineering and technical measures, neural network, resource optimization, meteorological data
1. Upravlenie riskami ekstremal'nyh yavlenij i bedstvij dlya prodvizheniya adaptacii k izmeneniyu klimata (Mezhpravitel'stvennaya gruppa ekspertov po izmeneniyu klimata (MGEIK) // Special'nyj doklad MGEIK po upravleniyu riskami ekstremal'nyh yavlenij i bedstvij dlya prodvizheniya adaptacii k izmeneniyu klimata. 2012. 594 s. URL: https://www.ipcc.ch/site/assets/uploads/2018/03/IPCC_SREX_RU_web-1.pdf (data obrashcheniya: 11.02.2025).
2. Evaluation of ensemble streamflow predictions in Europe / L. Alfieri [et al.] // Journal of Hydrology. 2014. Vol. 517. P. 913–922. DOI:https://doi.org/10.1016/j.jhydrol.2014.06.035.
3. Pappenberger F., Thielen J., Del Medico M. The impact of weather forecast improvements on large scale hydrology: analyzing a decade of forecasts of the European Flood Alert System // Hydrological Processes. 2011. Vol. 25. № 7. P. 1091–1113. DOI:https://doi.org/10.1002/hyp.7772.
4. Framing vulnerability, risk and societal responses: the MOVE framework /J. Birkmann [et al.] // Natural Hazards. 2013. Vol. 67. № 2. P. 193–211. DOI:https://doi.org/10.1007/s11069-013-0558-5.
5. Anaya-Arenas A.M., Renaud J., Ruiz A. Relief distribution networks: a systematic review // Annals of Operations Research. 2014. Vol. 223. № 1. P. 53–79. DOI:https://doi.org/10.1007/s10479-014-1581-y.
6. Rawls C.G., Turnquist M.A. Pre-positioning of emergency supplies for disaster response // Transportation Research Part B: Methodological. 2010. Vol. 44. № 4. P. 521–534. DOI:https://doi.org/10.1016/j.trb.2009.08.003.
7. Leveraging machine learning algorithms for improved disaster prediction and management / A. Linardos [et al.] // Frontiers in Environmental Science. 2023. Vol. 11. Article 1194918. DOI:https://doi.org/10.3389/fenvs.2023.1194918.
8. Lu L., Guo W. Automatic Quantification of Settlement Damage using Deep Learning of Satellite Images // arXiv preprint arXiv:2010.05512. 2020. URL: https://arxiv.org/abs/2010.05512 (data obrashcheniya: 28.01.2025).
9. Rybakov A.V., Posternak E.V. Aktual'nost' problemy povysheniya kachestva prognozirovaniya chrezvychajnyh situacij prirodnogo haraktera // Modelirovanie tekhnicheski slozhnyh processov i sistem: sb. trudov HXXIII Mezhdunar. nauch.-prakt. konf. Himki, 2023. S. 40–44.
10. MCHS Rossii. URL: https://mchs.gov.ru/deyatelnost/itogi-deyatelnosti-mchs-rossii (data obrashcheniya: 28.01.2025).
11. Evropejskaya ekonomicheskaya komissiya OON. Statisticheskaya baza dannyh EEK OON. URL: https://w3.unece.org/PXWeb/ru/ (data obrashcheniya: 28.01.2025).
12. Centr issledovanij epidemiologii katastrof. Mezhdunarodnaya baza dannyh o chrezvychajnyh situaciyah EM-DAT. URL: https://www.emdat.be/ (data obrashcheniya: 28.01.2025).
13. Novoselov I.E., Smirnov A.A., Zhidkov I.S. Izuchenie vliyaniya parametrov perovskitnyh solnechnyh batarej na ih effektivnost' pri pomoshchi mashinnogo obucheniya // Mezhdunarodnyj nauchno-issledovatel'skij zhurnal. 2024. № S5 (143). URL: https://research-journal.org/archive/5-143-2024-may/10.60797/IRJ.2024.143.121 (data obrashcheniya: 28.01.2025). DOI:https://doi.org/10.60797/IRJ.2024.143.121.
14. Rasina I.V. Diskretno-nepreryvnye modeli i optimizaciya upravlyaemyh processov // Programmnye sistemy: teoriya i prilozheniya. 2011. № 5. URL: https://cyberleninka.ru/article/n/diskretno-nepreryvnye-modeli-i-optimizatsiya-upravlyaemyh-protsessov (data obrashcheniya: 28.01.2025).
15. Agarkov Yu.Yu. Metody mashinnogo obucheniya dlya optimizacii proektirovaniya nejromorfnyh sistem // Innovacii i investicii. 2023. № 6. URL: https://cyberleninka.ru/article/n/metody-mashinnogo-obucheniya-dlya-optimizatsii-proektirovaniya-neyromorfnyh-sistem (data obrashcheniya: 28.01.2025).
16. Torkunova Yu.V., Milovanov D.V. Optimizaciya nejronnyh setej: metody i ih sravnenie na primere intellektual'nogo analiza teksta // IJAS. 2023. № 4. URL: https://cyberleninka.ru/article/n/optimizatsiya-neyronnyh-setey-metody-i-ih-sravnenie-na-primere-intellektualnogo-analiza-teksta (data obrashcheniya: 28.01.2025).
