Boletín de la Sociedad Geológica Mexicana Volumen 73, núm. 1, A031020, 2021 http://dx.doi.org/10.18268/BSGM2021v73n1a031020

Modelo de red neuronal para el pronóstico de la contaminación en polvos urbanos de principales vialidades de Bogotá, Colombia

Neuronal network model to predict pollution by urban dust from major passageways in Bogotá, Colombia

Rubén Cejudo¹, Germán Bayona², Avto Goguitchaichvili^1,*, Miguel Cervantes³, Francisco Bautista¹, Fabiola Mendiola⁴

¹Laboratorio Universitario de Geofísica Ambiental, Instituto de Geofísica, Universidad Nacional Autónoma de México, Antigua Carretera a Pátzcuaro 8701, Ex Hacienda de San José de la Huerta, 58190 Morelia, Michoacán, México.

²Corporación Geológica ARES, Calle 26 N. 69C-03 Torre C Of. 904 Bogotá D.C., Colombia.

³Escuela Nacional de Estudio Superiores, Unidad Morelia, Antigua Carretera a Pátzcuaro 8701, Ex Hacienda de San José de la Huerta, 58190 Morelia, Michoacán, México.

⁴Instituto de Geofísica, Universidad Nacional Autónoma de México, Antigua Carretera a Pátzcuaro 8701, Ex Hacienda de San José de la Huerta, 58190 Morelia, Michoacán, México.

* Autor para correspondencia: (R. Cejudo) This email address is being protected from spambots. You need JavaScript enabled to view it.

How to cite this article:

Cejudo, R., Bayona, G., Goguitchaichvili, A., Cervantes, M., Bautista, F., Mendiola, F., 2021, Modelo de red neuronal para el pronóstico de la contaminación en polvos urbanos de principales vialidades de Bogotá, Colombia: Boletín de la Sociedad Geológica Mexicana, 73 (1), A031020. http://dx.doi.org/10.18268/BSGM2021v73n1a031020

ABSTRACT

The use of artificial neuronal network (ANN) involves a limited number of variables to predict the behavior of some phenomena with promising results. Here, we used a simple ANN model to identify sites with high concentration heavy metals deduced from the magnetic parameters. The study was performed on urban dust samples belonging to main roads of the city of Bogota, Colombia. The results indicate an extensive distribution of magnetic material and heavy metals (Cr, Cu, Ni, Pb, V y Zn) in all studied areas. There are several sites with relatively high concentration of heavy metals showing the pollution load index above to 3. Several models of neural networks were tested while architecture 3 and 2 enables much reliable prediction of polluted sites showing correlation parameters 0.6 between actual and estimated values.

Keywords: Neuronal network, pollution, urban dust, monitoring.