Recurrent neural network using LSTM for prediction of atmospheric pollutants in the State of Veracruz, Mexico
DOI:
https://doi.org/10.38152/bjtv7n3-002Keywords:
artificial neural networks, LSTM, recurrent neural network, forecasting, atmospheric pollutants, deep learningAbstract
This article shows the use of a recurrent neural network LSTM whose objective was to make a 24-hour ozone forecast with data obtained from the INECC (National Institute of Ecology and Climate Change) and the validated database of the National Information System of Air Quality (SINAICA spanish acronym). The problem of air quality in the world is essential due to health problems. Currently, the techniques used to generate forecasts in monitoring stations are not accurate and do not allow generating alerts to avoid exposure to poor air quality. The state of Veracruz in Mexico has 7 air quality monitoring stations, showing that it is feasible to alternatively have a betterquality pollutant concentration forecasting system. The results obtained on the correlations of variables, although weak, positive or negative, allowed us to recognize their usefulness in the development of training in the RNN. The use of neural networks was demonstrated for the forecast of ozone concentration values in the metropolitan area of Poza Rica, using the LSTM using Python, Tensor Flow and Keras, with a good fit to the normalized pattern with an average RMSE of 0.0053 ppm of the days chosen for testing between the period from June 2019 to July 2020. Future work will consider PM10 and PM2.5.
References
ATHIRA V. GEETHA P., VINAYAKUMAR R., SOMAN K. P.(2018). DeepAirNet: Applying recurrent networks for Airquiality prediction. Procedia computer Science 132, pp 1394-1403.doi: https//doi.org/10.1016/j.procs.2018.05.068
CHIARVETTO P. l; REY S. F; AND BRIGNOLE N.B. (2008). Aplicación de redes neuronales artificiales para la predicción de calidad del aire. Mecánica computacional Vol XXVII.pp 3607-3625. Alberto Cardona, Mario Storti, Carlos Zuppa Eds. San Luis Argentina.
CHARDIN H.C., LOPEZ P. M.,SALAS R., TORRES R., CANAS R.P. Y LOPEZ GONZALEZ J.(2021). Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima-Peru. Scientific Reports 11:24232, doi: https://doir.org/10.1031/s41598-021-03650-9
CHOLLET, F. (2015). Keras: The Python deep learning API. Retrieved from https://keras.io/
FRITSCH S, Guenther F, Wright M (2019). _neuralnet: Training of Neural Networks_. R package version 1.44.2, disponible en https://CRAN.R-project.org/package=neuralnet.
GARCIA C.D. (2021). Prototipo de red neuronal para el pronóstico de eventos críticos por partículas PM2.5 en el centro de la ciudad de Manizalez. Los libertadores Fundación Universitaria.
JUNIOR, I. O., & dos Santos, F. C. C. (2022). INTELIGÊNCIA ARTIFICIAL E POLICIAMENTO PREDITIVO: possibilidades de inovação tecnológica para a Polícia Militar do Paraná no enfrentamento aos crimes violentos contra o patrimônio com emprego de explosivos. Brazilian Journal of Technology, 5(1), 030–062. https://doi.org/10.38152/bjtv5n1-003
NARESH G., INDIRA B., (2023). Air pollution prediction using multivariate LSTM Deep learning model. International Journal of Intelligent Systems and applications in engineering. UISAE. 12(8s) pp 211-220. ISSN: 2147-6799
OMS, (2024) Nota periodística: La OMS organizará la segunda conferencia mundial sobre la contaminación del aire y salud, disponible en https://www.who.int/es/news/item/19-06-2024-who-to-host-second-global-conference-on-air-pollution-and-health
Maria Neira, D. D. (12 de JULY de 2023). Air pollution: The invisible health threat. Obtenido de https://www.who.int/news-room/feature-stories/detail/air-pollution--the-invisible-health-threat
PROAire, (2018), GOBIERNO DEL ESTADO DE VERACRUZ: ProAire del Estado de Veracruz, disponible en https://www.gob.mx/cms/uploads/attachment/file/418382/31_ProAire_Veracruz.pdf
RAYBAUT, P. (2009). Spyder: A powerful scientific environment written in Python, for Python. Retrieved from https://www.spyder-ide.org/
TAHAN MONICA; (10 de julio 2019) video youtube Predicción con Redes Neuronales Artificiales en Rstudio; disponible en https://www.youtube.com/live/nMANuQ52p2E?si=JKzVWo4I_YM1a89l
TENSORFLOW. (2023). An open-source machine learning framework for everyone. Retrieved from https://www.tensorflow.org/
URIARTE, J. J. F., Salazar, A. G. A., Aguilasocho, M. A. Z., & Martagón, S. P. (2022). Implementation of artificial neural networks in the process of "support for permanence" of the polytechnic university of valle del évora as a proposal for decision making: Implementação de redes neurais artificiais no processo de "apoio à permanência" da universidade politécnica de valle del évora como uma proposta para a tomada de decisões. Brazilian Journal of Technology, 5(4), 208–223. https://doi.org/10.38152/bjtv5n4-002
ZHAO, Z, Qin, J. Z. et al. Combining fordward with recurrent neural networks for hourly air quality prediction in Northwest of China. Environ Sci Pollution Research 27, 28931-28948(2020), doi: https://doi.org/10.1007/s11356-020-08948-1
ZHAO X., ZHANG R., WU JL AND CHANG PC. (2018). A Deep recurrent neural network for air quality classification, Journal of InformationHiding and multimedia Signal Processing. Vol (9:2), pp 346-354, ISSN 2073-4212. Ubiquitous International.
ZHHIYU Chen, Yuzhu Zang, Gang Liu, Jianwei Guo, (2021), Air Quality Index Prediction Based on Deep Recurrent Neural Network; Artificial Intelligence and Security: 6th International Conference, ICAIS 2020, Hohhot, China, July 17–20, 2020, Proceedings, Part I, July 2020, Pages 291 – 304, doi: https://doi.org/10.1007/978-3-030-57884-8_2
