Hybrid computational model to assist in the location of victims buried in the tragedy of Brumadinho

Autores

  • Rafael Fernandes Pinheiro UNIVERSIDADE DE SÃO PAULO
  • Harold Ivan Angulo Bustos
  • Bruno Bestle Turrin
  • Francisco Marcos da Costa Monteiro
  • Diego Colón
  • Mirelly Ferreira Silveira
  • Dário José Aloise
  • Alysson Mendes de Oliveira

DOI:

https://doi.org/10.24221/jeap.6.3.2021.4103.183-193

Resumo

The rupture of dams in Brazil has caused great concern due to the environmental disaster and the loss of lives. The use of algorithms and computational models to assist search teams in locating victims when buried by tailings is essential but scarce. Those that exist are mainly slow, as they involve high computational costs. In this sense, in the context of the Brumadinho tragedy in 2019, this study aimed to develop a hybrid computational model to assist the search teams in locating victims buried by the tailings. The methodology for designing this model was based on regression techniques, machine learning, and physicomathematical algorithms. Firstly, the study resulted in a physicomathematical model based on integral and vector calculus and concepts of fluid mechanics, which provided results to assist in locating bodies buried by the tailings. More recently, based on data provided by the physicomathematical algorithm, two hybrid models have been developed. One uses statistical regression, and the other uses support vector regression, a type of machine learning. It is expected that a more accurate model can be used in other possible situations of disruption in future studies. Also, it is possible to apply the model developed in situations involving computational fluid dynamics in general.

Downloads

Não há dados estatísticos.

Referências

Alvarado, L. A. S. 2006. Two-dimensional simulation of debris runs using the Discrete Element Method (in Portuguese). Master's thesis. PUC-Rio. Rio de Janeiro, Brasil. 154p.

Weter, D.; Galvão, D. 2019. Brumadinho Dam has a volume of 12.7 million m³ of mining rejects. (in Portuguese). Cotidiano-Uol Notícias. Available at: https://noticias.uol.com.br/ultimas-noticias/agencia-estado/2019/01/25/barragem-em-brumadinho-tem-volume-de-1-milhao-de-m-de-rejeito-de-mineracao.htm. Access on: 31 August 2021.

Boser, B. E.; Guyon I. M.; Vapnik, V. N. 1992. A Training Algorithm for Optimal Margin Classifiers. In: D. Haussler (Ed.), COLT '92: Proceedings of the fifth annual workshop on Computational. New York: ACM Press. pp. 144-152.

Burden, R. L.; Faires, J. D.; Burden., A. M. 2015. Numerical Analysis. Cengage Learning. 912p.

Burges, C. J. 1998. A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery, 2, 121-167.

Daneshvar, P.; Zsaki, A. M. 2018. Simulation of tailings flow resulting from a dam breach using smoothed particle hydrodynamics. Environmental and Engineering Geoscience, 24, (3), 263-279.

Gomes., H. S. 2020. From mud to patent: scientists made Brumadinho's tragedy turn into innovation. (in Portuguese). Tilt-Uol Notícias. Available at: https://www.uol.com.br/tilt/noticias/redacao/2020/02/12/morte-na-lama-como-cientistas-inovaram-apos-tragedia-de-brumadinho.htm. Access on: 29 September 2020.

Guzman, S. M.; Paz, J. O.; Tagert, M. L. M. et al. 2019. Evaluation of Seasonally Classified Inputs for the Prediction of Daily Groundwater Levels: NARX Networks Vs Support Vector Machines. Environ Model Assess, 24, 223-234.

Li, X.; Luo, A.; Li, J. et al. 2019. Air Pollutant Concentration Forecast Based on Support Vector Regression and Quantum-Behaved Particle Swarm Optimization. Environ Model Assess, 24, 205-222.

Luo, C.; Xu, K.; Zhao, Y. 2017. A TVD discretization method for shallow water equations: Numerical simulations of tailing dam break. International Journal of Modeling, Simulation, and Scientific Computing, 08, (03), 1850001.

Marcolino, D. A.; Medina, A.; Rafael, C. M.; Amner, R. 2018. Periodic Steady State Assessment of Microgrids with Photovoltaic Generation Using Limit Cycle Extrapolation and Cubic Splines. Energies, 11, (8), 2096.

Moazenzadeh, R.; Mohammadi, B.; Shamshirband, S.; Chau, K. 2018. Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran. Engineering Applications of Computational Fluid Mechanics, 12, (1), 584-597.

Muson, B. R.; Young, D. F.; Okiishi, T. H. 2004. Fundamentos da Mecânica dos Fluidos. Edgar Blüsher. 584p.

Piovezan., S. 2019. How network of scientists uses data to try to find bodies in Brumadinho. (in Portuguese). Uol Notícias. Available at: https://www.uol.com.br/tilt/noticias/redacao/2019/03/08/cientistas-criam-rede-para-ajudar-vitimas-de-brumadinho-e-evitar-tragedias.htm. Access on: 29 September 2020.

Qasem, S. N.; Samadianfard, S.; Kheshtgar, S. et al. 2019. Modeling monthly pan evaporation using wavelet support vector regression and wavelet artificial neural networks in arid and humid climates. Engineering Applications of Computational Fluid Mechanics, 13, (1), 177-187.

Rehamnia, I.; Benlaoukli, B.; Heddam, S. 2020. Modeling of Seepage Flow Through Concrete Face Rockfill and Embankmen Dams Using Three Heuristic Artificial Intelligence Approaches: A Comparative Study. Environ. Process, 7, 367-381.

Santamaría-Bonfil, G.; Reyes-Ballesteros, A.; Gershenson., C. 2016. Wind speed forecasting for wind farms: A method based on support vector regression. Renewable Energy, 85, 790-809.

Seyedashraf, O.; Mehrabi, M.; Akhtari, A. A. 2018. Novel approach for dam break flow modeling using computational intelligence. Journal of Hydrology, Vol. 559.

Tabari, M. M. R.; Sanayei, H. R. Z. 2019. Prediction of the intermediate block displacement of the dam crest using artificial neural network and support vector regression models. Soft Comput, 23, 9629-9645.

Vacondio, R.; Palù, A. D.; Mignosa, P. 2014 GPU-enhanced Finite Volume Shallow Water solver for fast flood simulations. Environmental Modelling & Software, 57, 60-75.

Zhang, M., Xu, Y.; Qiao, H. 2018. Numerical Study of Hydrodynamic and Solute Transport with Discontinuous Flows in Coastal Water. Environ Model Assess, 23, 353-367.

Zhou, J.; Causon, D.; Mingham, C.; Ingram., D. 2004. Numerical Prediction of Dam Break Flows in General Geometries with Complex Bed Topography. Journal of Hydraulic Engireering, 130, (4), 332-340.

Publicado

2021-09-06