Redes Convolucionais Temporais para Previsão de Séries Epidemiológicas de COVID-19 no Período Pós-Pandêmico
Resumo
A previsão de séries temporais de COVID-19 permanece desafiadora no período pós-pandêmico devido à redução da testagem, subnotificação e quebras de regime. Este trabalho avalia Temporal Convolutional Networks (TCN) para previsão de longo prazo de casos em Nova York e no Brasil, sob um protocolo experimental unificado. A TCN é comparada com LSTM, RNN, ARIMA e SARIMA usando MAE, RMSE, MAPE e R2. Os resultados indicam melhor desempenho em Nova York, enquanto a série brasileira apresenta maior dificuldade devido à irregularidade e possível subnotificação. A TCN otimizada obteve o melhor desempenho geral e baixo custo de inferência, indicando potencial para monitoramento epidemiológico.
Referências
Amaral, F., Casaca, W., Oishi, C. M., and Cuminato, J. A. (2021). Simulating immunization campaigns and vaccine protection against COVID-19 pandemic in Brazil. IEEE Access, 9:126011–126022.
Arora, P., Kumar, D., and Bhatia, M. S. (2020). Forecasting of covid-19 spread using lstm and gru models. Chaos, Solitons & Fractals, 139:110030.
Bai, S., Kolter, J. Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271. Acesso em: 01 mar. 2026.
Capomaccio, S. (2024). Casos de covid-19 registram aumento e vacinação ainda é importante. Jornal da USP.
Chinazzi, M., Davis, J. T., Ajelli, M., et al. (2020). The effect of travel restrictions on the spread of the 2019 novel coronavirus (covid-19) outbreak. Science, 368(6489):395–400.
de Souza, G. N., Mendes, A. G. B., Costa, J. d. S., Oliveira, M. d. S., Lima, P. V. C., et al. (2023). Deep learning framework for epidemiological forecasting: A study on covid-19 cases and deaths in the amazon state of pará, brazil. PLOS ONE. Acesso em: 01 mar. 2026.
Dehning, J., Zierenberg, J., Spitzner, F. P., et al. (2020). Inferring change points in the spread of covid-19 reveals the effectiveness of interventions. Science, 369(6500):eabb9789.
Ferreira, R. S., Casaca, W., and Colnago, M. (2024). Aplicação de redes de deep learning recurrent neural network, long short-term memory e gated recurrent unit na predição da covid-19 no cenário pós-vacinação. In Seminário Integrado de Software e Hardware (SEMISH), pages 145–156. SBC.
Ferreira, R. S., Colnago, M., and Casaca, W. (2025). Predictive and interpretable machine learning for covid-19 resurgences: the role of sars-cov-2 variants in the post-pandemic era. BMC Infectious Diseases.
Flaxman, S., Mishra, S., Gandy, A., et al. (2020). Estimating the effects of non-pharmaceutical interventions on covid-19 in europe. Nature, 584(7820):257–261.
Hall, T. and Rasheed, K. (2025). A survey of machine learning methods for time series prediction. Applied Sciences.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.
Jin, W., Dong, S., Yu, C., and Luo, Q.-q. (2022). A data-driven hybrid ensemble ai model for covid-19 infection forecast using multiple neural networks and reinforced learning. Computers in Biology and Medicine. Acesso em: 01 mar. 2026.
Keras Team (2026). Earlystopping. [link]. Acesso em: 01 mar. 2026.
Khan, D. M., Ali, M., Iqbal, N., Khalil, U., Aljohani, H. M., Alharthi, A. S., and Afify, A. Z. (2022). Short-term prediction of covid-19 using novel hybrid ensemble empirical mode decomposition and error trend seasonal model. Frontiers in Public Health. Acesso em: 01 mar. 2026.
Kong, X., Chen, Z., Liu, W., Ning, K., Zhang, L., Muhammad Marier, S., Liu, Y., Chen, Y., and Xia, F. (2025). Deep learning for time series forecasting: a survey. International Journal of Machine Learning and Cybernetics, 16(7):5079–5112.
Krichen, M. and Mihoub, A. (2025). Long short-term memory networks: A comprehensive survey. AI.
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., and Hager, G. D. (2017). Temporal convolutional networks for action segmentation and detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Acesso em: 01 mar. 2026.
Lu, G., Ou, Y., Wang, Z., Qu, Y., Xia, Y., Tang, D., Kotenko, I., and Li, W. (2025). A survey of deep learning for time series forecasting: Theories, datasets, and state-of-the-art techniques. Computers, Materials and Continua, 85(2):2403–2441.
Masoorian, E., Teimoori, A., Bakhtiari, S., Jalilian, F. A., Vosough, R. N., and Ansari, N. (2025). Post-covid-19 seasonality of influenza, respiratory syncytial virus, and sars-cov-2 among hospitalized children in western iran: A molecular surveillance study (2023–2024). Journal of Epidemiology and Global Health.
Mendes, V. (2024). Por que covid-19 ainda mata tanta gente no brasil. BBC News Brasil.
Oliveira, C. (2024). Controle sobre a covid-19 ainda é instável no país após quatro anos do 1º caso. Brasil de Fato.
Shastri, S., Singh, K., Kumar, R., et al. (2021). Time series forecasting of covid-19 using deep learning models: India-usa comparative case study. Chaos, Solitons & Fractals, 140:110227.
Snoek, J., Larochelle, H., and Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems, volume 25. Curran Associates, Inc.
Snoek, J., Rippel, O., Swersky, K., Kiros, R., Satish, N., Sundaram, N., Patwary, M., Prabhat, M., and Adams, R. (2015). Scalable bayesian optimization using deep neural networks. In International conference on machine learning, pages 2171–2180. PMLR.
Suntronwong, N., Vichaiwattana, P., Puenpa, J., Pasittungkul, S., Aeemjinda, R., Wongsrisang, L., and Poovorawan, Y. (2025). Seasonal pattern and age-specific detection of eight respiratory viruses causing acute respiratory infection in 2024, bangkok, thailand. Tropical Medicine and Infectious Disease, 10(12):339.
Zeng, A., Chen, M., Zhang, L., and Xu, Q. (2023). Are transformers effective for time series forecasting? In Proceedings of the AAAI Conference on Artificial Intelligence.
Arora, P., Kumar, D., and Bhatia, M. S. (2020). Forecasting of covid-19 spread using lstm and gru models. Chaos, Solitons & Fractals, 139:110030.
Bai, S., Kolter, J. Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271. Acesso em: 01 mar. 2026.
Capomaccio, S. (2024). Casos de covid-19 registram aumento e vacinação ainda é importante. Jornal da USP.
Chinazzi, M., Davis, J. T., Ajelli, M., et al. (2020). The effect of travel restrictions on the spread of the 2019 novel coronavirus (covid-19) outbreak. Science, 368(6489):395–400.
de Souza, G. N., Mendes, A. G. B., Costa, J. d. S., Oliveira, M. d. S., Lima, P. V. C., et al. (2023). Deep learning framework for epidemiological forecasting: A study on covid-19 cases and deaths in the amazon state of pará, brazil. PLOS ONE. Acesso em: 01 mar. 2026.
Dehning, J., Zierenberg, J., Spitzner, F. P., et al. (2020). Inferring change points in the spread of covid-19 reveals the effectiveness of interventions. Science, 369(6500):eabb9789.
Ferreira, R. S., Casaca, W., and Colnago, M. (2024). Aplicação de redes de deep learning recurrent neural network, long short-term memory e gated recurrent unit na predição da covid-19 no cenário pós-vacinação. In Seminário Integrado de Software e Hardware (SEMISH), pages 145–156. SBC.
Ferreira, R. S., Colnago, M., and Casaca, W. (2025). Predictive and interpretable machine learning for covid-19 resurgences: the role of sars-cov-2 variants in the post-pandemic era. BMC Infectious Diseases.
Flaxman, S., Mishra, S., Gandy, A., et al. (2020). Estimating the effects of non-pharmaceutical interventions on covid-19 in europe. Nature, 584(7820):257–261.
Hall, T. and Rasheed, K. (2025). A survey of machine learning methods for time series prediction. Applied Sciences.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.
Jin, W., Dong, S., Yu, C., and Luo, Q.-q. (2022). A data-driven hybrid ensemble ai model for covid-19 infection forecast using multiple neural networks and reinforced learning. Computers in Biology and Medicine. Acesso em: 01 mar. 2026.
Keras Team (2026). Earlystopping. [link]. Acesso em: 01 mar. 2026.
Khan, D. M., Ali, M., Iqbal, N., Khalil, U., Aljohani, H. M., Alharthi, A. S., and Afify, A. Z. (2022). Short-term prediction of covid-19 using novel hybrid ensemble empirical mode decomposition and error trend seasonal model. Frontiers in Public Health. Acesso em: 01 mar. 2026.
Kong, X., Chen, Z., Liu, W., Ning, K., Zhang, L., Muhammad Marier, S., Liu, Y., Chen, Y., and Xia, F. (2025). Deep learning for time series forecasting: a survey. International Journal of Machine Learning and Cybernetics, 16(7):5079–5112.
Krichen, M. and Mihoub, A. (2025). Long short-term memory networks: A comprehensive survey. AI.
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., and Hager, G. D. (2017). Temporal convolutional networks for action segmentation and detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Acesso em: 01 mar. 2026.
Lu, G., Ou, Y., Wang, Z., Qu, Y., Xia, Y., Tang, D., Kotenko, I., and Li, W. (2025). A survey of deep learning for time series forecasting: Theories, datasets, and state-of-the-art techniques. Computers, Materials and Continua, 85(2):2403–2441.
Masoorian, E., Teimoori, A., Bakhtiari, S., Jalilian, F. A., Vosough, R. N., and Ansari, N. (2025). Post-covid-19 seasonality of influenza, respiratory syncytial virus, and sars-cov-2 among hospitalized children in western iran: A molecular surveillance study (2023–2024). Journal of Epidemiology and Global Health.
Mendes, V. (2024). Por que covid-19 ainda mata tanta gente no brasil. BBC News Brasil.
Oliveira, C. (2024). Controle sobre a covid-19 ainda é instável no país após quatro anos do 1º caso. Brasil de Fato.
Shastri, S., Singh, K., Kumar, R., et al. (2021). Time series forecasting of covid-19 using deep learning models: India-usa comparative case study. Chaos, Solitons & Fractals, 140:110227.
Snoek, J., Larochelle, H., and Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems, volume 25. Curran Associates, Inc.
Snoek, J., Rippel, O., Swersky, K., Kiros, R., Satish, N., Sundaram, N., Patwary, M., Prabhat, M., and Adams, R. (2015). Scalable bayesian optimization using deep neural networks. In International conference on machine learning, pages 2171–2180. PMLR.
Suntronwong, N., Vichaiwattana, P., Puenpa, J., Pasittungkul, S., Aeemjinda, R., Wongsrisang, L., and Poovorawan, Y. (2025). Seasonal pattern and age-specific detection of eight respiratory viruses causing acute respiratory infection in 2024, bangkok, thailand. Tropical Medicine and Infectious Disease, 10(12):339.
Zeng, A., Chen, M., Zhang, L., and Xu, Q. (2023). Are transformers effective for time series forecasting? In Proceedings of the AAAI Conference on Artificial Intelligence.
Publicado
19/07/2026
Como Citar
FERREIRA, Rafaella S.; CASACA, Wallace; BENVENUTO, Giovana A..
Redes Convolucionais Temporais para Previsão de Séries Epidemiológicas de COVID-19 no Período Pós-Pandêmico. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 53. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 698-709.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2026.21351.
