Russian Federation
Russian Federation
A scientific and methodological framework is presented for short-term forecasting of damage from natural disasters and for substantiating the required volumes of response personnel and technical equipment based on a cascade of machine learning models. A three-stage structure has been developed: M-1 – prediction of direct economic damage, M-2 – estimation of the number of deployed personnel, M-3 – determination of the need for technical equipment. The model integrates data from EM-DAT, reports of the Russian Ministry of Emergency Situations, Rosstat, and UNECE, supplemented with synthetic observations generated using the Gaussian Copula method. Three algorithms were compared: LightGBM, CatBoost, and a multilayer perceptron (MLP). On the hold-out test sample (20 % of observations; aggregation level – region; target – logarithm of direct damage), the MLP achieved a mean absolute error (MAE) of 350,075 thousand rubles R² = 0,35) for damage prediction, corresponding to the average absolute error per disaster event when compared with actual data. For estimating the required personnel and equipment, the mean absolute error was 32 people and 14 units of equipment, respectively, outperforming the boosting models (108–111 people and 41–62 units). SHAP analysis confirmed the key role of socio-demographic indicators in forecasting both damage and resource requirements. The scientific novelty of the study lies in the development of a reproducible cascade approach that combines short-term damage forecasting with resource allocation, making it applicable in agency-level operational planning systems. The methodology can be further scaled to technological and combined disaster scenarios.
short-term forecasting, disaster damage, response personnel and equipment, machine learning, SHAP analysis, socio-demographic factors, resource planning
1. Global'noe izmenenie klimata i ego posledstviya / L.V. Bondarenko [i dr.] // Vestnik REA im. G.V. Plekhanova. 2018. № 2 (98). URL: https://cyberleninka.ru/article/n/globalnoe-izmenenie-klimata-i-ego-posledstviya (data obrashcheniya: 11.06.2025).
2. A Comprehensive Review of Machine Learning Approaches for Flood Depth Estimation / B. Liu [et al.] // Int J Disaster Risk Sci. 2025. DOI:https://doi.org/10.1007/s13753-025-00639-0.
3. Development of Combined Heavy Rain Damage Prediction Models with Machine Learning / C. Choi [et al.] // Water. 2019. № 11. P. 2516. DOI:https://doi.org/10.3390/w11122516.
4. Using Disaster Outcomes to Validate Components of Social Vulnerability to Floods: Flood Deaths and Property Damage across the USA / B. Tellman [et al.] // Sustainability. 2020. № 12. P. 6006. DOI:https://doi.org/10.3390/su12156006 (data obrashcheniya: 11.06.2025).
5. Alekhin M.Yu., Yanchenko A.Yu., Krymskij V.V. O prognozirovanii ekonomicheskogo ushcherba ot chrezvychajnyh situacij // Nauchno-analiticheskij zhurnal «Vestnik Sankt-Peterburgskogo universiteta Gosudarstvennoj protivopozharnoj sluzhby MCHS Rossii». 2012. № 2. S. 84–88. URL: https://cyberleninka.ru/article/n/o-prognozirovanii-ekonomicheskogo-uscherba-ot-chrezvychaynyh-situatsiy (data obrashcheniya: 11.06.2025).
6. Rybakov A.V., Posternak E.V. Analiz problemnoj situacii v oblasti obosnovaniya ob"emov inzhenerno-tekhnicheskih meropriyatij pri prognozirovanii ushcherba ot prirodnyh chrezvychajnyh situacij s uchetom antropogennyh faktorov // Nauchnye i obrazovatel'nye problemy grazhdanskoj zashchity. 2024. № 4 (63). S. 72–83. EDN BJANZK.
7. Machine learning application to disaster damage repair cost modelling of residential buildings / N. Wanigarathna [et al.] // Construction Management and Economics. 2024. № 43 (4). P. 302–322. DOI:https://doi.org/10.1080/01446193.2024.2419413 (data obrashcheniya: 11.06.2025).
8. Hadzegov A.S., Krejtor V.P. Metody prognozirovaniya prirodnyh i tekhnogennyh opasnostej, riskov vozniknoveniya chrezvychajnyh situacij, dinamiki ih posledstvij, ocenke ushcherba // Aktual'nye issledovaniya. 2022. № 17 (96). S. 11–15. URL: https://apni.ru/article/4038-metodi-prognozirovaniya-prirodnikh-i-tekhnog (data obrashcheniya: 11.06.2025).
9. Caunhye A.M., Nie X., Pokharel S. Optimization models in emergency logistics: A literature review // Socio-economic planning sciences. 2012. T. 46. № 1. S. 4–13. DOI:https://doi.org/10.1016/j.seps.2011.04.004 (data obrashcheniya: 11.06.2025).
10. Rybakov A.V., Posternak E.V. Matematicheskaya model' obosnovaniya ob"emov inzhenerno-tekhnicheskih meropriyatij dlya minimizacii ushcherba ot prirodnyh chrezvychajnyh situacij s uchetom antropogennyh faktorov // Problemy upravleniya riskami v tekhnosfere. 2025. № 1 (73). S. 102–117. DOI:https://doi.org/10.61260/1998-8990-2025-1-102-117. EDN CCNPUD.
11. Machine Learning in Disaster Management: Recent Developments in Methods and Applications / V. Linardos [et al.] // Mach. Learn. Knowl. Extr. 2022. № 4. P. 446–473. DOI:https://doi.org/10.3390/make4020020 (data obrashcheniya: 11.06.2025).
12. Nikul'chev E.V., Chervyakov A.A. Postroenie robastnyh interval'nyh modelej prognozirovaniya dinamiki strukturno-slozhnoj sistemy // Trudy NGTU im. R.E. Alekseeva. 2023. № 1 (140). S. 33–41. URL: https://cyberleninka.ru/article/n/postroenie-robastnyh-intervalnyh-modeley-prognozirovaniya-dinamiki-strukturno-slozhnoy-sistemy (data obrashcheniya: 11.06.2025).
13. Shaptala V.G., Radouckij V.Yu., Shaptala V.V. Primenenie nejrosetevyh tekhnologij dlya prognozirovaniya chrezvychajnyh situacij // Vestnik BGTU im. V.G. SHuhova. 2011. № 2. S. 152–154.
14. Harin Yu.S. Ustojchivost' v statisticheskom prognozirovanii vremennyh ryadov // Prikladnaya ekonometrika. 2006. № 1. S. 82–92. URL: https://cyberleninka.ru/article/n/ustoychivost-v-statisticheskom-prognozirovanii-vremennyh-ryadov (data obrashcheniya: 11.06.2025).
15. O vybore metoda dinamicheskogo normirovaniya energoresursov neftepererabatyvayushchih proizvodstv / V.R. Vedruchenko [i dr.] // Omskij nauchnyj vestnik. Ser.: Aviacionno-raketnoe i energeticheskoe mashinostroenie. 2024. № 2. S. 5–12. URL: https://cyberleninka.ru/article/n/o-vybore-metoda-dinamicheskogo-normirovaniya-energoresursov-neftepererabatyvayuschih-proizvodstv (data obrashcheniya: 11.06.2025).
16. Analiz prognoznyh svojstv strukturnyh modelej i modelej s vklyucheniem rezul'tatov oprosov predpriyatij / V. Nosko [i dr.] // Nauchnye trudy Fonda «Institut ekonomicheskoj politiki im. E.T. Gajdara. 2003. № 64. URL: https://cyberleninka.ru/article/n/analiz-prognoznyh-svoystv-strukturnyh-modeley-i-modeley-s-vklyucheniem-rezultatov-oprosov-predpriyatiy (data obrashcheniya: 11.06.2025).
17. Lebedeva M.R., Lobashov A.O., Semchenkov S.S. Metody analiza dannyh i prognozirovaniya avarijnosti na primere goroda Minska // Vestnik Polockogo gosudarstvennogo universiteta. Ser. B.: Promyshlennost'. Prikladnye nauki. 2025. № 1. S. 70–76. URL: https://cyberleninka.ru/article/n/metody-analiza-dannyh-i-prognozirovaniya-avariynosti-na-primere-goroda-minska (data obrashcheniya: 11.06.2025).
