Air Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-Peru
Abstract The prediction of air pollution is of great importance in highly populated areas because it has a direct impact on both the management of the city's economic activity and the health of its inhabitants. In this work, the spatio-temporal behavior of air quality in Metropolitan Lima was e...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Lenguaje: | inglés |
| Publicado: |
2021
|
| Acceso en línea: | Descargar el archivo Enlace permanente (DOI o Handle) Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881508851895762944 |
|---|---|
| author | Cordova, Chardin Hoyos Lopez Portocarrero, Manuel Niño Salas, Rodrigo Torres, Romina Rodrigues, Paulo Canas López Gonzales, Javier Linkolk |
| author_browse | Cordova, Chardin Hoyos Lopez Portocarrero, Manuel Niño López Gonzales, Javier Linkolk Rodrigues, Paulo Canas Salas, Rodrigo Torres, Romina |
| author_facet | Cordova, Chardin Hoyos Lopez Portocarrero, Manuel Niño Salas, Rodrigo Torres, Romina Rodrigues, Paulo Canas López Gonzales, Javier Linkolk |
| author_sort | Cordova, Chardin Hoyos |
| collection | Producción científica |
| description | Abstract The prediction of air pollution is of great importance in highly populated areas because it has a direct impact on both the management of the city's economic activity and the health of its inhabitants. In this work, the spatio-temporal behavior of air quality in Metropolitan Lima was evaluated and predicted using the recurrent artificial neural network known as Long-Short Term Memory networks (LSTM). The LSTM was implemented for the hourly prediction of PM10 based on the past values of this pollutant and three meteorological variables obtained from five monitoring stations. The model was evaluated under two validation schemes: the hold-out (HO) and the blocked-nested cross-validation (BNCV). The simulation results show that periods of low PM10 concentration are predicted with high precision. Whereas, for periods of high contamination, the LSTM network with BNCV has better predictability performance. In conclusion, recurrent artificial neural networks with BNCV adapt more precisely to critical pollution episodes and have better performance to forecast this type of environmental data, and can also be extrapolated to other pollutants. |
| format | Preprint |
| id | oai:cris.upeu.edu.pe:20.500.15037/1339 |
| institution | UPeU |
| language | English |
| publishDate | 2021 |
| publishDateRange | 2021 |
| publishDateSort | 2021 |
| record_format | dspace |
| spelling | oai:cris.upeu.edu.pe:20.500.15037/13392026-11-02T22:00:04ZAir Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-PeruCordova, Chardin HoyosLopez Portocarrero, Manuel NiñoSalas, RodrigoTorres, RominaRodrigues, Paulo CanasLópez Gonzales, Javier LinkolkAbstract The prediction of air pollution is of great importance in highly populated areas because it has a direct impact on both the management of the city's economic activity and the health of its inhabitants. In this work, the spatio-temporal behavior of air quality in Metropolitan Lima was evaluated and predicted using the recurrent artificial neural network known as Long-Short Term Memory networks (LSTM). The LSTM was implemented for the hourly prediction of PM10 based on the past values of this pollutant and three meteorological variables obtained from five monitoring stations. The model was evaluated under two validation schemes: the hold-out (HO) and the blocked-nested cross-validation (BNCV). The simulation results show that periods of low PM10 concentration are predicted with high precision. Whereas, for periods of high contamination, the LSTM network with BNCV has better predictability performance. In conclusion, recurrent artificial neural networks with BNCV adapt more precisely to critical pollution episodes and have better performance to forecast this type of environmental data, and can also be extrapolated to other pollutants.Preprinthttps://www.researchsquare.com/article/rs-869832/latest.pdfhttps://doi.org/10.21203/rs.3.rs-869832/v110.21203/rs.3.rs-869832/v1https://hdl.handle.net/20.500.15037/1339W3200715984enResearch Square2021-09-092026-06-13T09:53:50Z2026-06-13T09:53:50Z |
| spellingShingle | Cordova, Chardin Hoyos Lopez Portocarrero, Manuel Niño Salas, Rodrigo Torres, Romina Rodrigues, Paulo Canas López Gonzales, Javier Linkolk Air Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-Peru |
| title | Air Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-Peru |
| title_full | Air Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-Peru |
| title_fullStr | Air Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-Peru |
| title_full_unstemmed | Air Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-Peru |
| title_short | Air Quality Assessment and Pollution Forecasting using Recurrent Artificial Neural Networks in Metropolitan Lima-Peru |
| title_sort | air quality assessment and pollution forecasting using recurrent artificial neural networks in metropolitan lima peru |
| url | https://www.researchsquare.com/article/rs-869832/latest.pdf https://doi.org/10.21203/rs.3.rs-869832/v1 https://hdl.handle.net/20.500.15037/1339 |
| work_keys_str_mv | AT cordovachardinhoyos airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu AT lopezportocarreromanuelnino airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu AT salasrodrigo airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu AT torresromina airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu AT rodriguespaulocanas airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu AT lopezgonzalesjavierlinkolk airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu |