Global passenger flows, comprising billions of trips annually, play a vital role in the global economy. Passenger traffic volumes exceeded 9.5 billion in 2024. Improving population mobility through increased access to high-quality transport services is a key priority for government transport policy. However, recent events have highlighted the instability of traditional methods for managing global passenger flows. The pandemic led to a 66% decline in passenger flows in 2020, highlighting the need for adaptive forecasting methods. Digital tools that help quickly assess passenger flows offer the potential to significantly improve the efficiency of global passenger transport. The author examines the challenges of forecasting and resilience in passenger flow management. Adaptive forecasting involves models that are adjusted based on current data using artificial intelligence and big data. Modern approaches to managing global passenger flows, including machine learning, improve forecast accuracy by 15-20%. Resilience in passenger flow management includes resistance to shocks and speed of recovery. The author's proposed adaptive forecasting model for global passenger flow management combines LSTM and scenario-based approaches. Adaptive forecasting and resilience are key trends for the sustainable development of global passenger flows. The goal of the study is to analyze these trends, develop a new forecasting model, and evaluate its contribution to resilience in global passenger flow management.
adaptive forecasting, resilience, passenger flows, machine learning, scenario modeling
1. Otchet o mirovom rynke passazhirskih perevozok za 2024 god. URL: https://ru.tripinfo.com/itm/articles/2024-global-source-passenger-market-report. (data obrascheniya: 19.12.2025 g.).
2. Agafonov A.A., Efimenko E.Yu. Prognozirovanie dvizheniya podklyuchennyh transportnyh sredstv v scenarii s adaptivnym upravleniem signalami svetoforov // IX Mezhdunarodnaya konferenciya i molodezhnaya shkola «Informacionnye tehnologii i nanotehnologii», 2023. – URL: https://repo.ssau.ru/bitstream/Informacionnye-tehnologii-i-nanotehnologii/Prognozirovanie-dvizheniya-podkluchennyh-transportnyh-sredstv-v-scenarii-s-adaptivnym-upravleniem-signalami-svetoforov-105981/1/978-5-7883-1919-3_2023-030422.pdf. (data obrascheniya: 19.12.2025 g.).
3. Rasporyazhenie Pravitel'stva RF ot 27.11.2021 N 3363-r (red. ot 06.11.2024) «O Transportnoy strategii Rossiyskoy Federacii do 2030 goda s prognozom na period do 2035 goda». URL: https://www.consultant.ru/document/cons_doc_LAW_402052/. (data obrascheniya: 19.12.2025 g.).
4. Miloserdov D.I. Usovershenstvovannaya sistema neyrosetevogo prognozirovaniya grupp vremennyh ryadov s nepreryvnym obucheniem // Informacionno-upravlyayuschie sistemy, 2024. – № 1 (128).
5. Fedoseev M.V. Analiz sovremennyh podhodov k ispol'zovaniyu sistemnoy analitiki bol'shih dannyh v prognozirovanii stoimosti aviabiletov // Vestnik nauki, 2025. – №4 (85).
6. Holling C.S. Resilience and Stability of Ecological Systems // Annual Review of Ecology and Systematics, 1973. – № 4. – P. 1-23.
7. Economic Performance of the Airline Industry, 2022. URL: https://www.iata.org/en/iata-repository/publications/economic-reports/airline-industry-economic-performance---october-2021---report/ (data obrascheniya: 20.12.2025).
8. Climate Change 2023: Synthesis Report, 2023. URL: https://www.ipcc.ch/report/ar4/wg1/climate-models-and-their-evaluation/ (data obrascheniya: 20.12.2025).
9. Vorob'ev A.V., Kashevarova G.G. Adaptivnye modeli kratkosrochnogo prognoza osedaniya zemnoy poverhnosti i opredelenie naibolee neblagopriyatnogo polozheniya zdaniya v mul'de sdvizheniya // Inzhenerno-stroitel'nyy zhurnal, 2013. – № 9. – S. 10-87.
10. Sovremennye sistemy i tehnologii na transporte: problemy i perspektivy: materialy Mezhdunarodnoy molodezhnoy nauchno-prakticheskoy konferencii, posvyaschennoy 95-letiyu VGLTU im. G.F. Morozova, Voronezh, 24-25 aprelya 2025 goda / otv. red. D.A. Zhayvoronok; M-vo nauki i vysshego obrazovaniya RF, FGBOU VO «VGLTU». – Voronezh, 2025. – 296 s.
11. Kadyrova G.M., Krasyukova N.L., Rozhdestvenskaya I.A., Tokmurzin T.M., Voronova E.I. Adaptivnaya optimizaciya transportnyh potokov vnutri podzemnyh vyrabotok na baze metodov iskusstvennogo intellekta // Gornaya promyshlennost', 2025. – № 1. – S. 137-146.
12. Antohonova I.V. Metody social'no-ekonomicheskogo prognozirovaniya: uchebnik dlya vuzov / I.V. Antohonova. – 2-e izd., ispr. i dop. – Moskva: Izdatel'stvo Yurayt, 2025. – 174 s.
13. Ignasheva T.A. Metody prognozirovaniya social'no-ekonomicheskih processov: uchebnoe posobie / T.A. Ignasheva. – Yoshkar-Ola: PGTU, 2018. – 104 s.
