Russian Federation
UDC 626.1
UDC 004.8
The paper considers the task of improving the transport infrastructure safety through the development of an intelligent simulation model. The focus is on predicting the water levels in lowland rivers to prevent emergencies such as flooding, bridge collapses and other crises that could disrupt transportation networks. The relevance of this research is determined by a variety of factors, including the rise in climatic hazards such as floods and heavy rainfall, industrial threats, and the limited efficacy of traditional approaches to monitoring and forecasting hydrological conditions. The study involves an analysis of actual emergency incidents, which starkly illustrates the urgent need for timely water level predictions. The methodology for developing a decision support system is based on machine learning technologies. The experimental component of the research utilizes data from the Temernik river. A total of 12 machine learning models were evaluated with the objective of selecting the most accurate and efficient models for future forecasting applications. The models were subjected to rigorous statistical assessment using a variety of performance metrics. Following the analysis, the most effective models have been identified and recommended for subsequent deployment and use.
transport infrastructure; emergencies; water level monitoring; intelligent simulation; decision support system; machine learning; water level predicting; AutoGluon; NeuralNetFastAI; WeightedEnsemble_L2; lowland rivers; risk management
1. Aref'eva E. V. Prognoz opasnostey na osnove postoyanno deystvuyuschey situacionno-optimizacionnoy modeli / E. V. Aref'eva, A. V. Rybakov // Vestnik KRSU. — 2012. — T. 12. — № 7. — S. 17–21.
2. Alagudzhaeva M. A. Gidrologicheskoe cifrovoe prognoznoe modelirovanie zon zatopleniya territorii Severnogo Kazahstana na osnove vysokodetal'noy cifrovoy modeli rel'efa / M. A. Alagudzhaeva, S. R. Sadvakasova, B. B. Elbasieva, A. A. Aimbetov // Gidrome-teorologiya i ekologiya. — 2023. — № 4. — S. 74–84. — DOI:https://doi.org/10.54668/2789-6323-2023-111-4-74-84.
3. Shu X. Knowledge Discovery: Methods from Data Mining and Machine Learning / X. Shu, Y. Ye // Social Science Research. — 2023. — Vol. 110. — P. 102817. — DOI: https://doi.org/10.1016/j.ssresearch.2022.102817.
4. Dolgih V. P. Kratkosrochnoe prognozirovanie vodnogo rezhima rek i vodohranilisch metodom Brauna / V. P. Dolgih, S. V. Rybalka, I. S. Bobleva // Ekologicheskiy vestnik Donbassa. — 2024. — № 2(12). — S. 10–15.
5. Cyganov V. V. Klimaticheskie riski zheleznodorozhnoy infrastruktury / V. V. Cyganov, V. A. Borodin, S. A. Savushkin, A. V. Lemeshkova // ITNOU: informacionnye tehnologii v nauke, obrazovanii i upravlenii. — 2024. — № 1(22)–2(23). — S. 51–57. — DOI: https://doi.org/10.47501/ITNOU.2024.1.51-57.
6. Vosstanovit' razorvannuyu nit': vosstanovlenie dvizheniya poezdov do Murmanska // Murmanskiy vestnik. — URL: https://www.mvestnik.ru/our-home/ vosstanovit'-razorvannuyunit'/ (data obrascheniya: 13.11.2025).
7. Obrushenie mosta // RIA «Voronezh». — URL: https:// riavrn.ru/theme/obrushenie-mosta/ (data obrascheniya: 13.11.2025).
8. V Rostove-na-Donu na vokzale podtopilo zheleznodorozhnye puti // TASS. — URL: https://tass.ru/ proisshestviya/21089611 (data obrascheniya: 13.11.2025).
9. Ermuhanov D. S. Mashinnoe obuchenie i matematika / D. S. Ermuhanov // Tendencii razvitiya nauki i obrazovaniya. — 2024. — № 110-18. — S. 102–105. — DOI:https://doi.org/10.18411/trnio-06-2024-992.
10. Chicco D. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation / D. Chicco, M. J. Warrens, G. Jurman // PeerJ Computer Science. — 2021. — Vol. 7. — Pp. 1–24. — DOI:https://doi.org/10.7717/PEERJ-CS.623.
11. Ponomarenko T. S. Izuchenie gidrologicheskih harakteristik reki Temernik po rezul'tatam raboty sistemy monitoringa «EMERSIT» / T. S. Ponomarenko, A. V. Breeva // Ekologiya i vodnoe hozyaystvo. — 2021. — № 2. — URL: https://cyberleninka.ru/article/n/izuchenie- gidrologicheskih-harakteristik-reki-temernikpo- rezultatam-raboty-sistemy-monitoringa-emersit (data obrascheniya: 30.10.2025).
12. Rashka S. Python i mashinnoe obuchenie. Mashinnoe i glubokoe obuchenie s ispol'zovaniem Python, scikit-learn i TensorFlow-2 / S. Rashka, V. Mirdzhalili. — M.: Vil'yams, 2020. — 848 s.
13. Mosin K. K. Ispol'zovanie metodov avtomatizirovannogo mashinnogo obucheniya dlya klassifikacii dorozhno-transportnyh proisshestviy / K. K. Mosin, V. E. Kovalevskiy, N. A. Zhukova // Intellektual'nye tehnologii na transporte. — 2023. — № 2(34). — URL: https://cyberleninka.ru/article/n/ispolzovanie-metodov-avtomatizirovannogo-mashinnogo-obucheniya-dlya- klassifikatsii-dorozhno-transportnyh-proisshestviy (data obrascheniya: 30.10.2025).
14. Feng K. RMSE-minimizing confidence intervals for the binomial parameter / K. Feng, L. M. Leemis, H. Sasinowska // Computational Statistics. — 2022. — Vol. 37. — Iss. 4. — Pp. 1855–1885. — DOI:https://doi.org/10.1007/s00180-021-01183-3.
