Forecasting the COVID-19 Space-time Dynamics in Brazil with Convolutional Graph Neural Networks and Transport Modals

Autores

  • Lucas Caldeira de Oliveira Universidade Tecnológica Federal do Paraná
  • Marcelo Teixeira Universidade Tecnológica Federal do Paraná
  • Dalcimar Casanova Universidade Tecnológica Federal do Paraná

Palavras-chave:

Covid-19, Graph Convolutional Network, Forecasting, Deep Learning

Resumo

This study presents a novel scalable method to forecast the numbers of cases and deaths by SARS-CoV-2 according to the influence that certain (micro) regions exert on others, predicting for specific regions while generalizing for general extents. By exploiting graph convolutional networks with recurrent networks, our approach maps the main access routes to municipalities in Brazil using the modals of transport, and processes this information via neural network algorithms. We compared the performance in forecasting the pandemic daily numbers with three baseline models, with the forecasting horizon varying from 1 to 25 days. Results show that the proposed model overcomes the baselines, being specially suitable for forecasts from 14 to 24 days ahead.

Downloads

Não há dados estatísticos.

Referências

Baud, D., Qi, X., Nielsen-Saines, K., Musso, D., Pomar, L., and Favre, G. (2020). Real estimates of mortality following COVID-19 infection. Infectious Deseases, 20.

Brasil.io (2020). Dataset covid-19. Accessed: 2021-01-25.

Cai, J., Xu, B., Chan, K. K. Y., Zhang, X., Zhang, B., Chen, Z., and Xu, B. (2019). Roles of different transport modes in the spatial spread of the 2009 influenza A (H1N1) pandemic in mainland China. International Journal of Environmental Research and Public Health, 16(2).

Da Silva, R. G., Ribeiro, M. H. D. M., Mariani, V. C., and dos Santos Coelho, L. (2020). Forecasting brazilian and american COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables. Chaos, Solitons & Fractals, 139:110027.

da Silva, T. T., Francisquini, R., and Nascimento, M. C. (2021). Meteorological and human mobility data on predicting covid-19 cases by a novel hybrid decomposition method with anomaly detection analysis: A case study in the capitals of brazil. Expert Systems with Applications, 182:115190.

Espinosa, M. M., de Oliveira, E. C., Melo, J. S., Damaceno, R. D., and Terças-Trettel, A. C. P. (2020). Predição de casos e óbitos de COVID-19 em Mato Grosso e no Brasil. Journal of Health & Biological Sciences, 8(1):1–7.

Galzo, W. (2021). Tempo médio até morte por COVID-19 em UTIs de SP caiu 4 dias no último trimestre. Accessed: 2021-03-26.

Garcia, R. (2020). Estudo mapeia tempo que COVID-19 leva para matar pacientes no Brasil. Accessed: 2021-03-26.

Han, E., Tan, M. M. J., Turk, E., Sridhar, D., Leung, G. M., Shibuya, K., Asgari, N., Oh, J., Garcı́a-Basteiro, A. L., Hanefeld, J., Cook, A. R., Hsu, L. Y., Teo, Y. Y., Heymann, D., Clark, H., McKee, M., and Legido-Quigley, H. (2020). Lessons learnt from easing covid-19 restrictions: an analysis of countries and regions in asia pacific and europe. The Lancet, 396(10261):1525–1534.

IBGE (2014). Logı́stica dos transportes – Brasil. Accessed: 2020-11-26.

IBGE (2019). Bases cartográficas contı́nuas – Brasil. Accessed: 2020-12-16.

IBGE, G. (2020). Covid-19 update. Accessed: 2021-01-25.

Lauer, S. A., Grantz, K. H., Bi, Q., Jone, F. K., Zheng, Q., Meredith, H. R., Azman, A. S., and Reich, Nicholas G. an Lessler, J. (2020). The incubation period of coronavirus disease 2019 (COVID-19) from publicly reported confirmed cases: Estimation and application. Annals of Internal Medicine, 172(9):577–582.

Li, Y., Tarlow, D., Brockschmidt, M., and Zemel, R. (2017). Gated graph sequence neural networks.

Lima, C., Silva, C., Silva, E., Marques, G., Araujo, L., Junior, L., Souza, S., Santana, M., Gomes, J., Barbosa, V., Musah, A., Kostkova, P., Dos Santos, W., and Silva-Filho, A. (2022). Monitoramento dinâmico e predição espaço-temporal da COVID-19 usando aprendizagem de máquina.

Pereira, I. G., Guerin, J. M., Silva Júnior, A. G., Garcia, G. S., Piscitelli, P., Miani, A., Distante, C., and Gonçalves, L. M. G. (2020). Forecasting COVID-19 dynamics in Brazil: A data driven approach. International Journal of Environmental Research and Public Health, 17(14):5115.

Ruan, Q., Yang, K., Wang, W., Jiang, L., and Song, J. (2020). Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan, China. Intensive Care Medicine.

SE/UNA-SUS (2021). Covid-19 update. Accessed: 2021-08-03.

Siqueira, E., Portela, C., Farias, F., and Braga, C. (2020). Temporal prediction model of the evolution of confirmed cases of the new coronavirus (SARS-CoV-2) in Brazil. IEEE Latin America Transactions, 100(1e).

Sktime (2020). Sktime documentation. Accessed: 2021-07-27.

Xu, B., Tian, H., Sabel, C. E., and Xu, B. (2019). Impacts of road traffic network and socioeconomic factors on the diffusion of 2009 pandemic influenza A (H1N1) in mainland China. International Journal of Environmental Research and Public Health, 16(7).

Downloads

Publicado

2022-07-21

Como Citar

Caldeira de Oliveira, L., Teixeira, M., & Casanova, D. (2022). Forecasting the COVID-19 Space-time Dynamics in Brazil with Convolutional Graph Neural Networks and Transport Modals. Revista Eletrônica De Iniciação Científica Em Computação, 20(3). Recuperado de https://sol.sbc.org.br/journals/index.php/reic/article/view/2683

Edição

Seção

Edição Especial: CTIC/CSBC