kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2026-23-3-328-335kaz29-3195Research ArticleМАТЕМАТИЧЕСКИЕ НАУКИMATHEMATICAL SCIENCESМОДИФИЦИРОВАННАЯ SEIR МОДЕЛЬ С GRID AUTO-SEARCH ОПТИМИЗАЦИЕЙ ДЛЯ ВЫСОКОТОЧНОГО ПРОГНОЗИРОВАНИЯ ДИНАМИКИ ЭПИДЕМИЙ НА ОСНОВЕ COVID-19MODIFIED SEIR MODEL WITH GRID AUTO-SEARCH OPTIMIZATION FOR HIGH-ACCURACY EPIDEMIC DYNAMICS FORECASTING BASED ON COVID-19https://orcid.org/0000-0002-2143-3994КуатбаеваA. A.KuatbaevaA. A.

PhD, ассистент-профессор

Астана

PhD, Assistant Professor

Astana

a.kuatbayeva@astanait.edu.kzhttps://orcid.org/0009-0007-8883-7073ОмарбековA. Н.OmarbekovA. N.

Магистр

Астана

MSc.

Astana

242929@astanait.edu.kzhttps://orcid.org/0009-0000-6188-8021АянА. А.AianA. A.

Магистр

Астана

MSc.

Astana

241785@astanait.edu.kzAstana IT universityКазахстанAstana IT universityKazakhstan202626092026233328335Copyright © Куатбаева A.A., Омарбеков A.Н., Аян А.А., 20262026Куатбаева A.A., Омарбеков A.Н., Аян А.А.Kuatbaeva A.A., Omarbekov A.N., Aian A.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/3195

В статье представлена модифицированная эпидемиологическая модель SEIR, интегрированная с методами машинного обучения для повышения точности прогнозирования динамики распространения COVID-19. Модель SEIR, более сложная, добавляет категорию «контактных» пациентов, которые способны передавать инфекцию, но еще не проявили симптомы. Такая модель позволяет лучше понять динамику эпидемий, особенно с длительным инкубационным периодом, который усложняет выявление заболевания и увеличивает риск его распространения. Предложенный подход расширяет классическую модель за счет временно-зависимых параметров, отражающих влияние мер социальной изоляции, уровня вакцинации и мобильности населения. Методология Grid Auto-Search обеспечивает автоматическую оптимизацию параметров и адаптивный выбор периода обучения. Для прогнозирования временно-зависимого коэффициента передачи β(t) применялись алгоритмы XGBoost и LSTM. Датасет включает 1143 наблюдения по Франции из трех открытых источников (Johns Hopkins University, Our World in Data, Google Mobility). Разработанная модель демонстрирует R² до 0,96 на горизонтах 30–90 дней; кросс-валидация подтверждает отсутствие существенного переобучения. Полученные результаты обосновывают практическую применимость гибридного подхода для систем поддержки принятия решений в здравоохранении. Результаты исследования подтверждены двумя авторскими свидетельствами Qazpatent на объекты авторского права.

This paper presents a modified SEIR epidemiological model integrated with machine learning techniques to improve COVID-19 transmission dynamics forecasting. The proposed approach extends the classical framework with time-dependent parameters capturing the effects of social distancing, vaccination coverage, and population mobility. The Grid Auto-Search methodology enables automatic parameter optimization and adaptive trainingperiod selection. XGBoost and LSTM algorithms are applied to forecast the time-varying transmission coefficient β(t). The dataset comprises 1,143 daily observations for France from three open sources (Johns Hopkins University, Our World in Data, Google Mobility). The model achieves R² up to 0.96 across 30–90-day horizons; crossvalidation confirms the absence of significant overfitting. The results support the practical applicability of this hybrid approach for healthcare decision-support systems. The research results are confirmed by two Qazpatent certificates of copyright registration.

SEIR модельCOVID-19эпидемиологическое прогнозированиеGrid Auto-Searchпараметрическая оптимизацияXGBoostLSTMвременные рядыматематическое моделированиемобильность населениявакцинацияSEIR modelCOVID-19epidemiological forecastingGrid Auto-Searchparameter optimizationXGBoostLSTMtime seriesmathematical modelingpopulation mobilityvaccinationReferencesOur World in Data. COVID-19 Data Repository (2024). URL: https://ourworldindata.org/coronavirus (accessed: October 15, 2025).Our World in Data. COVID-19 Data Repository (2024). URL: https://ourworldindata.org/coronavirus (accessed: October 15, 2025).Kermack, W.O., and McKendrick, A.G. A contribution to the mathematical theory of epidemics. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 115 (772), 700–721 (1927). https://doi.org/10.1098/rspa.1927.0118Kermack, W.O., and McKendrick, A.G. A contribution to the mathematical theory of epidemics. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 115 (772), 700–721 (1927). https://doi.org/10.1098/rspa.1927.0118Ahmad, N. COVID-19 modeling in Saudi Arabia using the modified susceptible-exposed-infectiousrecovered (SEIR) model. Cureus, 12 (9), e10452 (2020). https://doi.org/10.7759/cureus.10452Ahmad, N. COVID-19 modeling in Saudi Arabia using the modified susceptible-exposed-infectiousrecovered (SEIR) model. Cureus, 12 (9), e10452 (2020). https://doi.org/10.7759/cureus.10452Yang, Z., Zeng, Z., Wang, K., et al. Modified SEIR and AI prediction of the epidemic trend of COVID-19 in China under public health interventions. Journal of Thoracic Disease, 12 (3), 165–174 (2020). https://doi.org/10.21037/jtd.2020.02.64Yang, Z., Zeng, Z., Wang, K., et al. Modified SEIR and AI prediction of the epidemic trend of COVID-19 in China under public health interventions. Journal of Thoracic Disease, 12 (3), 165–174 (2020). https://doi.org/10.21037/jtd.2020.02.64Chen, S., Yu, J., Chamouni, S., Barnawi, A., Chen, X., and Xu, L. Integrating machine learning and artificial intelligence in life-course epidemiology: pathways to innovative public health solutions. BMC Medicine, 22, 354 (2024). https://doi.org/10.1186/s12916-024-03566-xChen, S., Yu, J., Chamouni, S., Barnawi, A., Chen, X., and Xu, L. Integrating machine learning and artificial intelligence in life-course epidemiology: pathways to innovative public health solutions. BMC Medicine, 22, 354 (2024). https://doi.org/10.1186/s12916-024-03566-xDong, E., Du, H., and Gardner, L. An interactive web-based dashboard to track COVID-19 in real time. The Lancet Infectious Diseases, 20 (5), 533–534 (2020). https://doi.org/10.1016/S1473-3099(20)30120-1Dong, E., Du, H., and Gardner, L. An interactive web-based dashboard to track COVID-19 in real time. The Lancet Infectious Diseases, 20 (5), 533–534 (2020). https://doi.org/10.1016/S1473-3099(20)30120-1Mathieu, E., Ritchie, H., Rodés-Guirao, L., Appel, C., Giattino, C., Hasell, J., Macdonald, B., Dattani, S., Beltekian, D., Ortiz-Ospina, E., and Roser, M. Coronavirus Pandemic (COVID-19). Our World in Data (2020). URL: https://github.com/owid/covid-19-data (accessed: October 15, 2025).Mathieu, E., Ritchie, H., Rodés-Guirao, L., Appel, C., Giattino, C., Hasell, J., Macdonald, B., Dattani, S., Beltekian, D., Ortiz-Ospina, E., and Roser, M. Coronavirus Pandemic (COVID-19). Our World in Data (2020). URL: https://github.com/owid/covid-19-data (accessed: October 15, 2025).Google LLC. Google COVID-19 Community Mobility Reports (2022). URL: https://www.google.com/covid19/mobility/ (accessed: October 15, 2025).Google LLC. Google COVID-19 Community Mobility Reports (2022). URL: https://www.google.com/covid19/mobility/ (accessed: October 15, 2025).Lu, M., Zheng, X.-Y., Jia, W.-N., and Tian, C.-Z. Analysis and prediction of improved SEIR transmission dynamics model: taking the second outbreak of COVID-19 in Italy as an example. Frontiers in Public Health, 11, 1223039 (2023). https://doi.org/10.3389/fpubh.2023.1223039Lu, M., Zheng, X.-Y., Jia, W.-N., and Tian, C.-Z. Analysis and prediction of improved SEIR transmission dynamics model: taking the second outbreak of COVID-19 in Italy as an example. Frontiers in Public Health, 11, 1223039 (2023). https://doi.org/10.3389/fpubh.2023.1223039Ghaffarzadegan, N., Rahmandad, H., and Jalali, M. Inefficiency of SIR models in forecasting the COVID-19 epidemic: a case study of Isfahan. Scientific Reports, 11, 4725 (2021). https://doi.org/10.1038/s41598-021-84055-6Ghaffarzadegan, N., Rahmandad, H., and Jalali, M. Inefficiency of SIR models in forecasting the COVID-19 epidemic: a case study of Isfahan. Scientific Reports, 11, 4725 (2021). https://doi.org/10.1038/s41598-021-84055-6Fernández Pozo, R., Rodríguez González, A.B., Vinagre Díaz, J.J., and Wilby, M.R. Data-driven analysis of the impact of COVID-19 on Madrid’s public transport during each phase of the pandemic. Cities, 124, 103574 (2022). https://doi.org/10.1016/j.cities.2022.103574Fernández Pozo, R., Rodríguez González, A.B., Vinagre Díaz, J.J., and Wilby, M.R. Data-driven analysis of the impact of COVID-19 on Madrid’s public transport during each phase of the pandemic. Cities, 124, 103574 (2022). https://doi.org/10.1016/j.cities.2022.103574Haghpanah, F., Lin, G., Levin, S.A., and Klein, E. Analysis of the potential impact of durability, timing, and transmission blocking of COVID-19 vaccine on morbidity and mortality. EClinicalMedicine, 35, 100863 (2021). https://doi.org/10.1016/j.eclinm.2021.100863Haghpanah, F., Lin, G., Levin, S.A., and Klein, E. Analysis of the potential impact of durability, timing, and transmission blocking of COVID-19 vaccine on morbidity and mortality. EClinicalMedicine, 35, 100863 (2021). https://doi.org/10.1016/j.eclinm.2021.100863Taghvaei, A., Georgiou, T.T., Norton, L., and Tannenbaum, A. Fractional SIR epidemiological models. Scientific Reports, 10, 20882 (2020). https://doi.org/10.1038/s41598-020-77849-7Taghvaei, A., Georgiou, T.T., Norton, L., and Tannenbaum, A. Fractional SIR epidemiological models. Scientific Reports, 10, 20882 (2020). https://doi.org/10.1038/s41598-020-77849-7Flouris, A.D., and Duffy, J. Applications of artificial intelligence systems in the analysis of epidemiological data. European Journal of Epidemiology, 21 (3), 167–170 (2006). https://doi.org/10.1007/ s10654-006-0005-yFlouris, A.D., and Duffy, J. Applications of artificial intelligence systems in the analysis of epidemiological data. European Journal of Epidemiology, 21 (3), 167–170 (2006). https://doi.org/10.1007/ s10654-006-0005-yLiu, L., Wang, X., Liu, O., Li, Y., Jin, Z., Tang, S., and Wang, X. Valuation and comparison of the actual and optimal control strategy in an emerging infectious disease: implication from a COVID-19 transmission model. Infectious Disease Modelling, 9 (2), 354–372 (2024). https://doi.org/10.1016/j.idm.2024.01.002Liu, L., Wang, X., Liu, O., Li, Y., Jin, Z., Tang, S., and Wang, X. Valuation and comparison of the actual and optimal control strategy in an emerging infectious disease: implication from a COVID-19 transmission model. Infectious Disease Modelling, 9 (2), 354–372 (2024). https://doi.org/10.1016/j.idm.2024.01.002

The authors declare that there are no conflicts of interest present.