Modeling Epidemics: Neural Network Based on Data and SIR-Model

O. I. Krivorotko; Криворотько О. И.; N. Yu. Zyatkov; Зятьков Н. Ю.; S. I. Kabanikhin; Кабанихин С. И.

doi:10.31857/S0044466923100095

Modeling Epidemics: Neural Network Based on Data and SIR-Model

Authors: Krivorotko O.I.¹, Zyatkov N.Y.¹, Kabanikhin S.I.¹
Affiliations:
1. Sobolev Institute of Mathematics, Siberian Branch of the Russian Academy of Sciences
Issue: Vol 63, No 10 (2023)
Pages: 1733-1746
Section: ИНФОРМАТИКА
URL: https://journals.rcsi.science/0044-4669/article/view/140296
DOI: https://doi.org/10.31857/S0044466923100095
EDN: https://elibrary.ru/MCDEIS
ID: 140296

Cite item

Full Text

Open Access
Restricted Access

Access granted
Restricted Access

Subscription Access

Abstract
About the authors
References
Supplementary files
Statistics

Abstract

Earlier, a method for constructing an initial approximation for solving the inverse problem of acoustics by a gradient method based on a convolutional neural network trained to predict the distribution of velocities in a medium from wave response was proposed [9]. It was shown that the neural network trained on responses from simple layered media can be successfully used for solving the inverse problem for a significantly more complex model. In this paper, we present algorithms for processing data about epidemics and an example of applying a neural network for modeling the propagation of COVID-19 in Novosibirsk region (Russia) based only on data. A neural network NN-COVID-19 that uses data about the epidemics is constructed. It is shown that this neural network predicts the propagation of COVID-19 for five days by an order of magnitude better than SEIR-HCD. When a new variant (Omicron) appeared, this neural network was able to predict (after retraining) the propagation of the epidemics more accurately. Note that the proposed neural network uses not only epidemiological data but also social ones (such as holidays, restrictive measures, etc.). The proposed approach makes it possible to refine mathematical models. A comparison of the curves constructed by SEIR-HCD model and by the neural network shows that the plots of solutions of the direct problem almost coincide with the plots constructed by the neural network. This helps refine coefficients of the differential model.

Keywords

epidemiology, time series, machine learning, deep learning, data processing, recurrent neural networks, fully connected neural networks, COVID-19, prediction, forcasting

References

Zyatkov N., Krivorotko O. Forecasting recessions in the US economy using machine learning methods // The 17th International Asian school-seminar “Optimization problems of complex systems” (OPCS). 2021. P. 139–146. https://doi.org/10.1109/OPCS53376.2021.9588678
Chen S., Guo W. Auto-encoders in deep learning – a review with new perspectives // Mathematics 2023. V. 11. P. 1–54.
Jie Gui, Zhenan Sun, Yonggang Wen, Dacheng Tao, Jieping Ye. A review on generative adversarial networks: algorithms, theory, and applications // IEEE Transact. on Knowledge and Data Engineer. 2023. V. 35. № 4. P. 3313–3332.
Ling J., Jones R., Templeton J. Physics-informed machine learning: A new paradigm for computational mechanics // Comput. Meth. Appl. Mech. Engineer. 2016. V. 309. P. 209–233.
Leyva-Vallina M., Nagy Z. Data-driven vs. physics-based modeling: A comparison from an industrial perspective // Chemic. Engineer. Sci. 2018. V. 182. P. 80–93.
Huang Y., Zhang J., Yang X., Drury C.F., Reynolds W.D., Tan C.S. Comparing the performance of machine learning algorithms for predicting soil organic carbon stocks in different land use systems // Geoderma. 2020. V. 375. P. 114448.
Brunton S.L., Proctor J.L., Kutz J.N. Discovering governing equations from data by sparse identification of nonlinear dynamical systems // Proceed. Nation. Acad. Sci. 2016. V. 113. № 15. P. 3932–3937.
Криворотько О.И., Кабанихин С.И. Математические модели распространения COVID-19. Препринт Ин-та матем. им. С.Л. Соболева СО РАН. 2022. № 300. 63 с.
Петров И.Б., Станкевич А.С., Васюков А.В. О поиске начального приближения в задаче волновой инверсии с помощью сверточных нейронных сетей // Докл. АН, 2023.
Nikparvar B., Rahman M.M., Hatami F., et al. Spatio-temporal prediction of the COVID-19 pandemic in US counties: modeling with a deep LSTM neural network // Sci. Rep. 2021. V. 11. P. 21715.
Shawaqfah M., Almomani F. Forecast of the outbreak of COVID-19 using artificial neural network: Case study Qatar, Spain, and Italy // Result. Phys. 2021. V. 27. P. 104484.
Гузев М.А., Никитина Е.Ю. Динамика “имперских хвостов” на примере коронавирусной инфекции // Дальневосточный матем. журн. 2022. Т. 22. № 1. С. 38–50.
Криворотько О.И., Кабанихин С.И., Зятьков Н.Ю., Приходько А.Ю., Прохошин Н.М., Шишленин М.А. Математическое моделирование и прогнозирование COVID-19 в Москве и Новосибирской области // Сиб. журн. вычисл. матем. 2020. Т. 23. № 4. С. 395–414.
Krivorotko O.I., Zyatkov N.Y. Data-driven regularization of inverse problem for SEIR-HCD model of COVID-19 propagation in Novosibirsk region // Eurasian J. Math. and Comput. Appl. 2022. V. 10. Iss. 1. P. 51–68.
Chen T., Guestrin C. XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining // ACM. 2016. P. 785–794.
Hochreiter S., Schmidhuber J. Long short-term memory // Neural Computat. 1997. V. 9. № 8. P. 1735–1780.
Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting // J. Mach. Learn. Res. 2014. V. 15. № 1. P. 1929–1958.
Ioffe S., Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift // Inter. Conf. Mach. Learn. 2015. V. 37. P. 448–456.
Nair V., Hinton G.E. Rectified linear units improve restricted Boltzmann machines // Proceed. of the 27th Inter. Conf. Mach. Learn. (ICML-10). 2010. P. 807–814.