Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú
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 p...
Guardado en:
| Autores principales: | , |
|---|---|
| Otros Autores: | |
| Formato: | Tesis de pregrado |
| Lenguaje: | inglés |
| Publicado: |
Universidad Peruana Unión
2021
|
| Materias: | |
| Acceso en línea: | Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881510285765771264 |
|---|---|
| author | Hoyos Cordova, Chardin Lopez Portocarrero, Manuel Niño |
| author2 | Lopez Gonzales, Javier Linkolk |
| author_browse | Hoyos Cordova, Chardin Lopez Gonzales, Javier Linkolk Lopez Portocarrero, Manuel Niño |
| author_facet | Lopez Gonzales, Javier Linkolk Hoyos Cordova, Chardin Lopez Portocarrero, Manuel Niño |
| author_sort | Hoyos Cordova, Chardin |
| collection | Repositorio institucional |
| description | 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. |
| escuela_str_mv | Escuela Profesional de Ingeniería Ambiental |
| format | info:eu-repo/semantics/bachelorThesis |
| id | oai:repositorio.upeu.edu.pe:20.500.12840/4837 |
| institution | UPeU |
| language | English |
| linea_str_mv | Gestión Ambiental |
| ocde_area_str_mv | Ingeniería y tecnología |
| ocde_disciplina_str_mv | Ingeniería ambiental |
| ocde_str_mv | 2.07.00 |
| programa_nombre_str_mv | Ingeniería Ambiental |
| programa_uri_str_mv | http://upeu.edu.pe/sys/programas/programa/ingenieria-ambiental |
| publishDate | 2021 |
| publishDateRange | 2021 |
| publishDateSort | 2021 |
| publisher | Universidad Peruana Unión |
| publisherStr | Universidad Peruana Unión |
| record_format | dspace |
| sede_str_mv | Lima |
| spelling | Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú Air quality assessmentand pollution forecasting using recurrent artificial neural networks in Metropolitan Lima-Peru Hoyos Cordova, Chardin Lopez Portocarrero, Manuel Niño Lopez Gonzales, Javier Linkolk Air pollution Air quality Recurrent artificial neural networks Time-series forecasting 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. 2021-08-23 2021-10-12T17:33:46Z 2021-10-12T17:33:46Z info:eu-repo/semantics/bachelorThesis https://hdl.handle.net/20.500.12840/4837 eng info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/3.0/es/ application/pdf Universidad Peruana Unión PE oai:repositorio.upeu.edu.pe:20.500.12840/4837 2026-11-10T17:45:09Z |
| spellingShingle | Air pollution Air quality Recurrent artificial neural networks Time-series forecasting Hoyos Cordova, Chardin Lopez Portocarrero, Manuel Niño Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú |
| title | Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú |
| title_full | Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú |
| title_fullStr | Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú |
| title_full_unstemmed | Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú |
| title_short | Evaluación de la calidad del aire y predicción de la contaminación utilizando redes neuronales artificiales recurrentes en Lima Metropolitana-Perú |
| title_sort | evaluacion de la calidad del aire y prediccion de la contaminacion utilizando redes neuronales artificiales recurrentes en lima metropolitana peru |
| topic | Air pollution Air quality Recurrent artificial neural networks Time-series forecasting |
| topic_facet | Air pollution Air quality Recurrent artificial neural networks Time-series forecasting |
| url | https://hdl.handle.net/20.500.12840/4837 |
| work_keys_str_mv | AT hoyoscordovachardin evaluaciondelacalidaddelaireypredicciondelacontaminacionutilizandoredesneuronalesartificialesrecurrentesenlimametropolitanaperu AT lopezportocarreromanuelnino evaluaciondelacalidaddelaireypredicciondelacontaminacionutilizandoredesneuronalesartificialesrecurrentesenlimametropolitanaperu AT hoyoscordovachardin airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu AT lopezportocarreromanuelnino airqualityassessmentandpollutionforecastingusingrecurrentartificialneuralnetworksinmetropolitanlimaperu |